WO2021182185A1 - Information processing device, system, and control method - Google Patents

Information processing device, system, and control method Download PDF

Info

Publication number
WO2021182185A1
WO2021182185A1 PCT/JP2021/007965 JP2021007965W WO2021182185A1 WO 2021182185 A1 WO2021182185 A1 WO 2021182185A1 JP 2021007965 W JP2021007965 W JP 2021007965W WO 2021182185 A1 WO2021182185 A1 WO 2021182185A1
Authority
WO
WIPO (PCT)
Prior art keywords
captured image
processor
interface
input
image
Prior art date
Application number
PCT/JP2021/007965
Other languages
French (fr)
Japanese (ja)
Inventor
佑介 宇佐美
朝日 一隆
昌孝 佐藤
Original Assignee
株式会社 東芝
東芝インフラシステムズ株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社 東芝, 東芝インフラシステムズ株式会社 filed Critical 株式会社 東芝
Priority to CA3169733A priority Critical patent/CA3169733A1/en
Priority to EP21767087.6A priority patent/EP4120128A4/en
Priority to AU2021235688A priority patent/AU2021235688B2/en
Publication of WO2021182185A1 publication Critical patent/WO2021182185A1/en
Priority to US17/929,845 priority patent/US20220413623A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/12Detection or correction of errors, e.g. by rescanning the pattern
    • G06V30/127Detection or correction of errors, e.g. by rescanning the pattern with the intervention of an operator
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
    • G06F3/0233Character input methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/98Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/14Image acquisition
    • G06V30/148Segmentation of character regions
    • G06V30/153Segmentation of character regions using recognition of characters or words
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/19Recognition using electronic means
    • G06V30/191Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • G06V30/42Document-oriented image-based pattern recognition based on the type of document
    • G06V30/424Postal images, e.g. labels or addresses on parcels or postal envelopes

Definitions

  • An embodiment of the present invention relates to an information processing device, a system, and a control method.
  • a recognition system equipped with a recognition device that reads character strings such as addresses by OCR (optical character recognition) processing, and a VCS (video coding system) that accepts character string input from the operator when the recognition device fails to recognize the character string.
  • OCR optical character recognition
  • VCS video coding system
  • an information processing device a system and a control method capable of effectively acquiring a character string are provided.
  • the information processing device includes an image interface, an input interface, a communication interface, and a processor.
  • the image interface is a display screen image based on at least the captured image displayed on the display screen of the input device from the input device for inputting the character string included in the captured image in which the recognition of the character string by the first algorithm fails.
  • the input interface inputs a character string into the input device.
  • the communication interface acquires the captured image from the image acquisition device.
  • the processor searches for the captured image corresponding to the display screen image, acquires a character string based on the result of character recognition processing of the searched captured image by a second algorithm different from the first algorithm, and obtains a character string.
  • the character string is input to the input device through the input interface.
  • FIG. 1 is a block diagram showing a configuration example of a recognition system according to an embodiment.
  • FIG. 2 is a block diagram showing a configuration example of the first recognition device according to the embodiment.
  • FIG. 3 is a block diagram showing a configuration example of the VCS according to the embodiment.
  • FIG. 4 is a block diagram showing a configuration example of the matching device according to the embodiment.
  • FIG. 5 is a block diagram showing a configuration example of the second recognition device according to the embodiment.
  • FIG. 6 is a diagram showing an example of an input screen according to the embodiment.
  • FIG. 7 is a flowchart showing an operation example of the first recognition device according to the embodiment.
  • FIG. 8 is a flowchart showing an operation example of the VCS according to the embodiment.
  • FIG. 1 is a block diagram showing a configuration example of a recognition system according to an embodiment.
  • FIG. 2 is a block diagram showing a configuration example of the first recognition device according to the embodiment.
  • FIG. 3 is a block diagram showing a
  • FIG. 9 is a flowchart showing an operation example of the second recognition device according to the embodiment.
  • FIG. 10 is a flowchart showing an operation example of the second recognition device according to the embodiment.
  • FIG. 11 is a flowchart showing an operation example of the matching device according to the embodiment.
  • the recognition system reads a destination such as an address from an article put into the sorter.
  • the recognition system sets the destination of the article (eg, sorter shoot) based on the read destination.
  • the recognition system accepts the input of the destination from the operator who visually checks the destination.
  • FIG. 1 shows a configuration example of the recognition system 1 according to the embodiment.
  • the recognition system 1 includes a sorter 2, a camera 3, a first recognition device 10, a VCS 20 (20a to 20d), a matching device 30 (30a to 30d), and an operation unit 40 (40a and 40b).
  • a display unit 50 (50a and 50b), a second recognition device 60, and the like are provided.
  • the first recognition device 10 is connected to the sorter 2, the camera 3, and the VCS 20.
  • the VCSs 20a to 20d are connected to the matching devices 30a to 30d, respectively.
  • the matching devices 30a and 30b are connected to the operation units 40a and 40b, respectively. Further, the matching devices 30a and 30b are connected to the display units 50a and 50b, respectively.
  • the second recognition device 60 is connected to the camera 3 and the matching device 30.
  • the recognition system 1 may further include a configuration as required in addition to the configuration shown in FIG. 1, or a specific configuration may be excluded from the recognition system 1.
  • the sorter 2 classifies the items to be input into the suppliers based on the signal from the first recognition device 10.
  • the sorter 2 includes a plurality of shoots as a partition.
  • the sorter 2 puts the article into the chute based on the signal from the first recognition device 10.
  • the sorter 2 acquires assortment information indicating an ID for identifying an article and a supplier (for example, a chute number) for inserting the article from the first recognition device 10.
  • the sorter 2 puts an article into the chute based on the sorting information.
  • the camera 3 (image acquisition device) captures an article to be put into the sorter 2.
  • the camera 3 captures a surface (destination surface) on which the destination of the article is described.
  • the camera 3 is installed on a transport path for loading articles into the sorter 2.
  • the camera 3 may capture an article from a plurality of surfaces.
  • the camera 3 transmits the captured image to the first recognition device 10 and the second recognition device 60.
  • the first recognition device 10 sets the sort destination of the article in the sorter 2 based on an image (captured image) or the like from the camera 3. For example, the first recognition device 10 transmits to the sorter 2 the sorting information indicating the ID for identifying the article and the partition to which the article is put.
  • the first recognition device 10 will be described in detail later.
  • the VCS20 is an input device for inputting a destination included in the captured image (captured image of the destination surface) in which the recognition of the destination fails when the first recognition device 10 fails to recognize the destination. VCS20 will be described in detail later.
  • the matching device 30 (information processing device) inputs the destination from the second recognition device 60 to the VCS 20.
  • the matching device 30 will be described in detail later.
  • the operation unit 40 receives inputs for various operations from the operator.
  • the operation unit 40 transmits a signal indicating the input operation to the matching device 30.
  • the operation unit 40 is composed of a keyboard, buttons, a touch panel, and the like.
  • the display unit 50 displays information based on the control from the matching device 30.
  • the display unit 50 is composed of a liquid crystal monitor.
  • the display unit 50 is composed of a liquid crystal monitor integrally formed with the operation unit 40.
  • the recognition system 1 may include an operation unit and a display unit connected to the matching devices 30c and 30d, respectively.
  • the second recognition device 60 recognizes the destination from the captured image by OCR processing (character recognition processing).
  • the second recognition device 60 transmits the captured image and the recognized destination to the matching device 30.
  • FIG. 2 shows a configuration example of the first recognition device 10.
  • the first recognition device 10 includes a processor 11, a memory 12, an operation unit 13, a display unit 14, a camera interface 15, a communication interface 16, and the like.
  • the processor 11 and the memory 12, the operation unit 13, the display unit 14, the camera interface 15, and the communication interface 16 are communicably connected to each other via a data bus, a predetermined interface, or the like.
  • the first recognition device 10 may further include a configuration as required in addition to the configuration as shown in FIG. 2, or a specific configuration may be excluded from the first recognition device 10.
  • the processor 11 controls the operation of the first recognition device 10 as a whole. For example, the processor 11 generates sorting information based on the recognition result of the destination and transmits it to the sorter 2.
  • the processor 11 is composed of a CPU and the like. Further, the processor 11 may be composed of an ASIC (Application Specific Integrated Circuit) or the like. Further, the processor 11 may be composed of an FPGA (Field Programmable Gate Array) or the like.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • the memory 12 stores various data.
  • the memory 12 functions as a ROM, RAM and NVM.
  • the memory 12 stores a control program, control data, and the like.
  • the control program and control data are preliminarily incorporated according to the specifications of the first recognition device 10.
  • the control program is a program that supports the functions realized by the first recognition device 10.
  • the memory 12 temporarily stores data and the like being processed by the processor 11. Further, the memory 12 may store data necessary for executing the application program, an execution result of the application program, and the like.
  • the operation unit 13 receives inputs for various operations from the operator.
  • the operation unit 13 transmits a signal indicating the input operation to the processor 11.
  • the operation unit 13 is composed of a keyboard, buttons, a touch panel, and the like.
  • the display unit 14 displays information based on the control from the processor 11.
  • the display unit 14 is composed of a liquid crystal monitor.
  • the display unit 14 is composed of a liquid crystal monitor integrally formed with the operation unit 13.
  • the camera interface 15 is an interface for transmitting and receiving data to and from the camera 3.
  • the camera interface 15 is connected to the camera 3 by wire.
  • the camera interface 15 receives the captured image from the camera 3.
  • the camera interface 15 transmits the received captured image to the processor 11. Further, the camera interface 15 may supply electric power to the camera 3.
  • the communication interface 16 is an interface for transmitting and receiving data to and from the sorter 2 and the VCS 20.
  • the communication interface 16 supports a LAN (Local Area Network) connection.
  • the communication interface 16 may support a USB (Universal Serial Bus) connection.
  • the communication interface 16 may be composed of an interface for transmitting and receiving data with the first recognition device 10 and an interface for transmitting and receiving data with the VCS 20.
  • VCS 20 Since VCS20a to 20d have the same configuration, they will be described as VCS20.
  • FIG. 3 shows a configuration example of VCS20.
  • the VCS 20 includes a processor 21, a memory 22, an operation unit interface 23, a display unit interface 24, a communication interface 25, and the like.
  • the processor 21, the memory 22, the operation unit interface 23, the display unit interface 24, and the communication interface 25 are communicably connected to each other via a data bus, a predetermined interface, or the like.
  • the VCS 20 may further include a configuration as required, or a specific configuration may be excluded from the VCS 20.
  • the processor 21 controls the operation of the entire VCS20. For example, the processor 21 outputs a captured image that fails to recognize the destination through the display unit interface 24.
  • the processor 21 is composed of a CPU and the like. Further, the processor 21 may be composed of an ASIC or the like. Further, the processor 21 may be composed of an FPGA or the like.
  • the memory 22 stores various data.
  • the memory 22 functions as a ROM, RAM and NVM.
  • the memory 22 stores a control program, control data, and the like.
  • the control program and control data are preliminarily incorporated according to the specifications of the VCS20.
  • the control program is a program that supports the functions realized by the VCS20.
  • the memory 22 temporarily stores data and the like being processed by the processor 21. Further, the memory 22 may store data necessary for executing the application program, an execution result of the application program, and the like.
  • the operation unit interface 23 is an interface for transmitting and receiving data to and from an input device that receives input for operations.
  • the operation unit interface 23 receives an operation signal indicating an operation (key input operation) input to the keyboard from the input device.
  • the operation unit interface 23 transmits the received operation signal to the processor 21.
  • the operation unit interface 23 may supply electric power to the input device.
  • the operating unit interface 23 supports a USB connection.
  • the display unit interface 24 is an interface for transmitting and receiving data to and from a display device that displays an image.
  • the display unit interface 24 outputs the image data from the processor 21 to the display device.
  • the communication interface 25 is an interface for transmitting and receiving data to and from the first recognition device 10 and the matching device 30.
  • the communication interface 25 supports a LAN connection.
  • the communication interface 25 may support a USB connection.
  • the communication interface 25 may be composed of an interface for transmitting and receiving data with the first recognition device 10 and an interface for transmitting and receiving data with the matching device 30.
  • the matching device 30 will be described. Since the matching devices 30a to 30d have the same configuration, they will be described as the matching device 30.
  • FIG. 4 shows a configuration example of the matching device 30.
  • the matching device 30 includes a processor 31, a memory 32, an image interface 33, an input interface 34, an operation unit interface 35, a display unit interface 36, a communication interface 37, and the like.
  • the processor 31 and the memory 32, the image interface 33, the input interface 34, the operation unit interface 35, the display unit interface 36, and the communication interface 37 are communicably connected to each other via a data bus or a predetermined interface.
  • the matching device 30 may further include a configuration as required, or a specific configuration may be excluded from the matching device 30.
  • the processor 31 controls the operation of the entire matching device 30. For example, the processor 31 inputs the destination from the second recognition device 60 to the VCS 20.
  • the processor 31 is composed of a CPU and the like. Further, the processor 31 may be composed of an ASIC or the like. Further, the processor 31 may be composed of an FPGA or the like.
  • the memory 32 stores various data.
  • the memory 32 functions as a ROM, RAM and NVM.
  • the memory 32 stores a control program, control data, and the like.
  • the control program and control data are preliminarily incorporated according to the specifications of the matching device 30.
  • the control program is a program that supports the functions realized by the matching device 30.
  • the memory 32 temporarily stores data and the like being processed by the processor 31. Further, the memory 32 may store data necessary for executing the application program, an execution result of the application program, and the like.
  • the image interface 33 is connected to the display interface 24 of the VCS 20.
  • the image interface 33 acquires an image from the display interface 24. That is, the image interface 33 acquires an image that the processor 21 of the VCS 20 intends to display on the display device.
  • the image interface 33 transmits the acquired image to the processor 31.
  • the image interface 33 is composed of a capture board or the like.
  • the input interface 34 is connected to the operation unit interface 23.
  • the input interface 34 inputs an operation signal indicating a key input operation to the operation unit interface 23 according to the control from the processor 31.
  • the input interface 34 supports a USB connection.
  • the operation unit interface 35 is an interface for transmitting and receiving data to and from the operation unit 40.
  • the operation unit interface 35 receives an operation signal indicating an operation input to the operation unit 40 from the operation unit 40.
  • the operation unit interface 35 transmits the received operation signal to the processor 31.
  • the operation unit interface 35 may supply electric power to the operation unit 40.
  • the operating unit interface 35 supports a USB connection.
  • the display unit interface 36 is an interface for transmitting and receiving data to and from the display unit 50.
  • the display unit interface 36 outputs the image data from the processor 31 to the display unit 50.
  • the communication interface 37 (second communication interface) is an interface for transmitting and receiving data to and from the VCS20, another matching device 30, and the second recognition device 60.
  • the communication interface 37 supports a LAN connection.
  • the communication interface 37 may support a USB connection.
  • the communication interface 37 is composed of an interface for transmitting and receiving data to and from the VCS 20, an interface for transmitting and receiving data to and from the other matching device 30, and an interface for transmitting and receiving data to and from the second recognition device 60. It may be configured.
  • matching devices 30c and 30d do not have to include the operation unit interface 35 and the display unit interface 36.
  • FIG. 5 shows a configuration example of the second recognition device 60.
  • the second recognition device 60 includes a processor 61, a memory 62, an operation unit 63, a display unit 64, a camera interface 65, a communication interface 66, and the like.
  • the processor 61, the memory 62, the operation unit 63, the display unit 64, the camera interface 65, and the communication interface 66 are communicably connected to each other via a data bus, a predetermined interface, or the like.
  • the second recognition device 60 may further include a configuration as required in addition to the configuration as shown in FIG. 2, or a specific configuration may be excluded from the second recognition device 60.
  • the processor 61 controls the operation of the entire second recognition device 60. For example, the processor 61 acquires a destination from a captured image.
  • the processor 61 is composed of a CPU and the like. Further, the processor 61 may be composed of an ASIC (Application Specific Integrated Circuit) or the like. Further, the processor 61 may be composed of an FPGA (Field Programmable Gate Array) or the like.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • the memory 62 stores various data.
  • the memory 62 functions as a ROM, RAM and NVM.
  • the memory 62 stores a control program, control data, and the like.
  • the control program and control data are preliminarily incorporated according to the specifications of the second recognition device 60.
  • the control program is a program that supports the functions realized by the second recognition device 60.
  • the memory 62 temporarily stores data and the like being processed by the processor 61. Further, the memory 62 may store data necessary for executing the application program, an execution result of the application program, and the like.
  • the operation unit 63 receives inputs for various operations from the operator.
  • the operation unit 63 transmits a signal indicating the input operation to the processor 61.
  • the operation unit 63 includes a keyboard, buttons, a touch panel, and the like.
  • the display unit 64 displays information based on the control from the processor 61.
  • the display unit 64 is composed of a liquid crystal monitor.
  • the display unit 64 is composed of a liquid crystal monitor integrally formed with the operation unit 63.
  • the camera interface 65 (image acquisition device interface) is an interface for transmitting and receiving data to and from the camera 3.
  • the camera interface 65 is connected to the camera 3 by wire.
  • the camera interface 65 receives the captured image from the camera 3.
  • the camera interface 65 transmits the received captured image to the processor 61.
  • the communication interface 66 (first communication interface) is an interface for transmitting and receiving data to and from the matching device 30.
  • the communication interface 66 supports a LAN connection.
  • the communication interface 66 may support a USB connection.
  • the function realized by the first recognition device 10 is realized by the processor 11 executing a program stored in the memory 12 or the like.
  • the processor 11 has a function of acquiring an captured image including a destination surface from the camera 3.
  • the camera 3 captures an image at the timing when the article passes through the imaging region of the camera 3.
  • the camera 3 transmits the captured image to the first recognition device 10.
  • the processor 11 acquires an captured image including the destination surface from the camera 3 through the camera interface 15.
  • the processor 11 may send a request to the camera 3 and receive a response including the captured image.
  • the processor 11 has a function of acquiring a destination from the captured image by OCR processing.
  • the processor 11 When the captured image is acquired, the processor 11 performs OCR processing on the captured image according to a predetermined algorithm (first algorithm). When the OCR process is performed, the processor 11 acquires the destination described on the destination surface of the article based on the result of the OCR process.
  • a predetermined algorithm first algorithm
  • the processor 11 has a function of acquiring a destination by using the VCS20 when the OCR process fails.
  • the processor 11 transmits the captured image to the VCS 20 through the communication interface 16.
  • the processor 11 selects one VCS20 from the VCSs 20a to 20d, and transmits the captured image to the selected VCS20.
  • the VCS 20 transmits the destination described on the destination surface included in the captured image to the first recognition device 10.
  • the processor 11 acquires a destination from the VCS 20 through the communication interface 16.
  • the processor 11 has a function of setting a supplier of articles based on a destination acquired by OCR processing or a destination from VCS20.
  • the processor 11 sets the number of the chute into which the article is inserted in the sorter 2 as the supplier based on the destination. For example, the processor 11 sets the number of the shoot corresponding to the destination administrative division (prefecture, municipality, etc.).
  • the processor 11 transmits the sorting information indicating the ID for identifying the article and the sorting destination of the article to the sorter 2 through the communication interface 16.
  • the function realized by the VCS 20 is realized by the processor 21 executing a program stored in the memory 22 or the like.
  • the processor 21 has a function of acquiring an captured image including a destination surface from the first recognition device 10.
  • the processor 11 of the first recognition device 10 transmits the captured image to the VCS 20 when the OCR process fails.
  • the processor 21 of the VCS 20 acquires the captured image from the first recognition device 10 through the communication interface 25.
  • the processor 21 has a function of transmitting the acquired captured image to the matching device 30.
  • the processor 21 When the captured image is acquired, the processor 21 generates an input screen (display screen) that accepts the input of the destination reflected in the captured image.
  • the input screen includes the acquired captured image.
  • FIG. 6 shows an example of the input screen 100 generated by the processor 21.
  • the input screen 100 includes an image area 101, an input field 102, and the like.
  • the image area 101 displays an captured image (display screen image) acquired from the first recognition device 10.
  • the image area 101 displays an captured image including the destination surface.
  • the image resolution of the character string included in the captured image displayed by the image area 101 may be lower than the image resolution of the character string included in the captured image captured by the camera 3.
  • the input field 102 is formed in the lower part of the image area 101.
  • the input field 102 accepts the input of the destination described on the destination surface of the captured image displayed by the image area 101.
  • the input screen 100 may include an icon or the like for confirming the input to the input field 102. Further, the input field 102 may be formed in the upper part of the image area 101.
  • the configuration of the input screen is not limited to a specific configuration.
  • the processor 21 When the input screen is generated, the processor 21 outputs the input screen generated through the display unit interface 24.
  • the processor 21 outputs an input screen in the same manner as when a display device is connected to the display unit interface 24. That is, the processor 21 outputs a signal similar to the signal output to a display device such as a display through the display unit interface 24.
  • the processor 21 has a function of accepting the input of the destination through the operation unit interface 23.
  • the processor 21 When the input screen is output, the processor 21 receives the input of the destination through the operation unit interface 23. The processor 21 acquires the same signal (operation signal indicating a key input operation) as when the operation unit is connected to the operation unit interface 23.
  • the processor 21 has a function of transmitting an input-accepted destination (information indicating the destination) to the first recognition device 10.
  • the processor 21 When the processor 21 receives an operation signal whose input is confirmed through the operation unit interface 23 (for example, an operation signal for which the enter key is pressed), the processor 21 transmits the destination input through the communication interface 25 to the first recognition device 10. ..
  • the function realized by the second recognition device 60 is realized by the processor 61 executing a program stored in the memory 62 or the like.
  • the processor 61 has a function of acquiring an captured image including a destination surface from the camera 3.
  • the processor 61 acquires a captured image from the camera 3 through the camera interface 65.
  • the processor 61 acquires an captured image similar to the captured image acquired by the first recognition device 10 from the camera 3.
  • the processor 61 has a function of acquiring a destination from the captured image by OCR processing.
  • the processor 61 When the captured image is extracted, the processor 61 performs OCR processing on the captured image according to a predetermined algorithm (second algorithm) different from the first algorithm.
  • the second algorithm can recognize at least a part of the character image that the first algorithm cannot recognize.
  • the processor 61 acquires the destination described on the destination surface of the article based on the result of the OCR processing.
  • the processor 61 When a plurality of captured images are acquired, the processor 61 performs OCR processing on each captured image and acquires a destination based on the result of the OCR processing.
  • the processor 61 associates the captured image with the destination and stores it in the memory 62.
  • the processor 61 may store the destination as the file name of the captured image.
  • the processor 61 may set an image ID or the like in the captured image.
  • the processor 61 has a function of associating the captured image with the destination and transmitting the captured image to the matching device 30.
  • the processor 61 receives a request for a captured image and a destination from the matching device 30 through the communication interface 66.
  • the request requests an captured image captured by the camera 3 (or acquired by the processor 61 during a predetermined period) in a predetermined period and a destination corresponding to the captured image.
  • the processor 61 acquires the captured image and the destination from the memory 62 according to the request. Upon acquiring the captured image and the destination, the processor 61 transmits a response including the captured image and the destination to the matching device 30 through the communication interface 66.
  • the function realized by the matching device 30 is realized by the processor 31 executing a program stored in the memory 32 or the like.
  • the processor 31 has a function of acquiring an input screen from the VCS 20.
  • the processor 31 acquires an input screen through an image interface 33 connected to the display interface 24 of the VCS 20. That is, the processor 31 acquires the captured image including the destination surface from the VCS 20.
  • the processor 31 has a function of acquiring the captured image and the destination corresponding to the captured image from the second recognition device 60.
  • the processor 31 estimates the time when the captured image included in the input screen is captured by the camera 3 based on the time when the input screen is acquired. For example, the processor 31 estimates the time when the camera 3 is imaged based on the time from when the camera 3 captures the image until the first recognition device 10 recognizes the destination and the VCS 20 outputs the input screen. ..
  • the processor 31 estimates a period (estimated period) having a predetermined width as the time when the camera 3 is imaged. For example, the processor 31 acquires, as an estimated period, a period between a time that is a predetermined time back from the time when the input screen is acquired and a time that a predetermined time has elapsed from the time.
  • the processor 31 transmits a request for an image captured during the estimation period (candidate image) and a destination corresponding to the image through the communication interface 37.
  • the processor 31 receives the response including the candidate captured image and the destination from the second recognition device 60 through the communication interface 37.
  • the processor 31 has a function of searching the captured image included in the input screen from the acquired candidate captured images. That is, the processor 31 searches for a candidate captured image corresponding to the captured image included in the input screen.
  • the processor 31 matches the candidate captured image with the captured image included in the input screen according to a predetermined algorithm.
  • the processor 31 calculates the degree of similarity between each candidate captured image and the captured image included in the input screen.
  • the processor 31 identifies the candidate captured image corresponding to the similarity and the captured image included in the input screen.
  • the method by which the processor 31 searches for the captured image included in the input screen from the candidate captured images is not limited to a specific method.
  • the processor 31 has a function of inputting a destination corresponding to the searched candidate captured image to the operation unit interface 23 of the VCS 20.
  • the processor 31 acquires the destination corresponding to the captured image and the identified candidate captured image.
  • the processor 31 inputs the acquired destination to the operation unit interface 23 of the VCS 20 through the input interface 34. That is, the processor 31 inputs an operation signal indicating a key input operation for inputting a destination to the operation unit interface 23.
  • the processor 31 may input an operation signal indicating an operation for completing the input of the destination to the operation unit interface 23.
  • the processor 31 has a function of inputting an operation signal indicating an operation input to the operation unit 40 to the operation unit interface 23 when the search for the captured image included in the input screen fails.
  • the processor 31 determines that the search for the captured image included in the input screen has failed.
  • the processor 31 displays the input screen from the VCS 20 on the display unit 50.
  • the processor 31 accepts the input to the operation unit 40.
  • the processor 31 Upon receiving the input to the operation unit 40, the processor 31 inputs an operation signal indicating the input operation to the operation unit interface 23.
  • the processor 31 may update the input screen on the display unit 50. That is, the processor 31 acquires the input screen from the display unit interface 24 in real time and displays it on the display unit 50.
  • the operator visually observes the image area of the input screen displayed on the display unit 50 and inputs the destination to the operation unit 40.
  • the operator inputs the operation to complete the input to the operation unit 40.
  • the processor 31 displays the input screen on the display unit 50 connected to the other matching device 30. Further, the processor 31 inputs an operation signal indicating an operation input to the operation unit 40 connected to the other matching device 30 to the operation unit interface 23 of the VCS 20.
  • the main matching device 30 (for example, the matching device 30a) or the external control device may manage the operation unit 40 used for input and the display unit 50 for displaying the input screen.
  • FIG. 7 is a flowchart for explaining an operation example of the first recognition device 10.
  • the processor 11 of the first recognition device 10 acquires an captured image including the destination surface of the article through the camera interface 15 (S11).
  • the processor 11 performs OCR processing on the captured image according to the first algorithm (S12).
  • the processor 11 transmits the captured image to the VCS20 through the communication interface 16 (S14).
  • the processor 11 determines whether or not the destination has been received from the VCS 20 through the communication interface 16 (S15).
  • the processor 11 If it is determined that the destination has not been received from the VCS20 (S15, NO), the processor 11 returns to S15.
  • the processor 11 determines the destination acquired by the OCR processing or the destination received from the VCS20. Based on the above, the sorter 2 is set to the supplier of the article (S16). When the sorting destination of the article is set in the sorter 2, the processor 11 ends the operation.
  • FIG. 8 is a flowchart for explaining an operation example of the VCS20.
  • the processor 11 of the VCS 20 determines whether or not the captured image has been received from the first recognition device 10 through the communication interface 25 (S21). If it is determined that the captured image has not been received from the first recognition device 10 (S21, NO), the processor 11 returns to S21.
  • the processor 21 When it is determined that the captured image has been received from the first recognition device 10 (S21, YES), the processor 21 outputs an input screen including the captured image through the display unit interface 24 (S22).
  • the processor 21 determines whether or not the input of the destination has been accepted through the operation unit interface 23 (S23). If it is determined that the input of the destination is not accepted (S23, NO), the processor 21 returns to S23.
  • the processor 21 transmits the input destination to the first recognition device 10 (S24) through the communication interface 25.
  • the processor 21 ends the operation.
  • FIG. 9 is a flowchart for explaining an operation example in which the second recognition device 60 acquires a destination.
  • the processor 61 of the second recognition device 60 acquires an captured image including the destination surface of the article through the camera interface 65 (S31).
  • the processor 61 performs OCR processing on the captured image according to the first algorithm (S32).
  • the processor 61 associates the captured image with the destination and stores the destination in the memory 62 (S34).
  • FIG. 10 is a flowchart for explaining an operation example in which the second recognition device 60 transmits a captured image and a destination.
  • the processor 61 of the second recognition device 60 determines whether or not a request has been received from the matching device 30 through the communication interface 66 (S41). If it is determined that the request has not been received (S41, NO), the processor 61 returns to S41.
  • the processor 61 acquires the captured image and the destination from the memory 62 according to the received request (S42). Upon acquiring the captured image and the destination, the processor 61 transmits a response including the captured image and the destination to the matching device 30 through the communication interface 66 (S43). When the response is transmitted, the processor 61 ends the operation.
  • FIG. 11 is a flowchart for explaining an operation example of the matching device 30.
  • the processor 31 of the matching device 30 determines whether or not the input screen has been acquired through the image interface 33 (S51). If it is determined that the input screen has not been acquired (S51, NO), the processor 31 returns to S51.
  • the processor 31 acquires the captured image (candidate captured image) and the destination based on the time when the input screen is acquired from the second recognition device 60 (S52).
  • the processor 31 searches for the captured image included in the input screen from each candidate captured image (S53).
  • the processor 31 acquires the destination corresponding to the candidate captured image identified as the captured image (S55).
  • the processor 31 inputs an operation signal indicating a key input operation for inputting the destination through the input interface 34 to the operation unit interface 23 of the VCS 20 (S56).
  • the processor 31 displays the input screen on the display unit 50 (S57).
  • the processor 31 inputs an operation signal indicating the operation input to the operation unit 40 to the operation unit interface 23 of the VCS 20 (S58).
  • the processor 31 executes S58 until it receives the input of the operation for which the input is completed.
  • the estimated period may be extended to acquire the captured image and the destination from the second recognition device 60.
  • the processor 31 searches for the captured image included in the input screen again.
  • the processor 31 may perform OCR processing on the captured image acquired by the second recognition device 60 according to the second algorithm to acquire the destination. For example, when the processor 31 of the second recognition device 60 acquires the captured image from the camera 3, the processor 31 transmits the captured image to one of the matching devices 30. The processor 31 of the matching device 30 performs OCR processing on the received captured image to acquire the destination. When the destination is acquired, the processor 31 transmits the acquired destination to the second recognition device 60. The processor 61 of the second recognition device 60 stores the captured image and the received destination in the memory 62 in association with each other.
  • the OCR processing by the second algorithm may be performed by both the matching device 30 and the second recognition device 60. Further, the OCR processing by the second algorithm may be executed by an external device. For example, the OCR processing by the second algorithm is executed by cloud computing. In this case, the processor 61 of the second recognition device 60 transmits the captured image to the external device. The processor 61 acquires the result of the OCR process from the external device.
  • the function of the second recognition device 60 may be performed by any of the matching devices 30.
  • the matching device 30 may be connected to a plurality of operation units and display units. Further, the matching device 30 may be integrally formed with the operation unit and the display unit.
  • first recognition device 10 may be integrally formed with the VCS 20. Further, the first recognition device 10 may be integrally formed with the camera 3. Further, the first recognition device 10 may be integrally formed with the sorter 2.
  • the VCS 20 may include an operation unit and a display unit.
  • the recognition system 1 may recognize a character string other than the destination of the article.
  • the character string recognized by the recognition system 1 is not limited to a specific configuration.
  • the recognition system configured as described above acquires captured images in advance from the camera connected to the first recognition device.
  • the recognition system 1 performs OCR processing on the captured image in advance according to a second algorithm different from the first algorithm of the first recognition device.
  • the recognition system stores the destination based on the result of the OCR process in a memory or the like in advance.
  • the recognition system acquires the captured image from the VCS in which the first recognition device fails to recognize the destination.
  • the recognition system searches for an captured image that matches the captured image from the VCS from the captured image acquired in advance.
  • the recognition system inputs the destination corresponding to the searched captured image into the VCS.
  • the recognition system can effectively acquire the destination without modifying the first recognition device.
  • the recognition system can input the destination to the VCS at high speed by storing the destination based on the OCR processing according to the second algorithm in advance.
  • the recognition system performs OCR processing according to the second algorithm based on the high-resolution captured image. Can be done.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Quality & Reliability (AREA)
  • Character Discrimination (AREA)
  • Character Input (AREA)
  • Hardware Redundancy (AREA)
  • Communication Control (AREA)

Abstract

The present invention provides an information processing device, a system, and a control method that can effectively acquire character strings. According to an embodiment, an information processing device includes an image interface, an input interface, a communication interface, and a processor. The image interface acquires, from an input device for inputting a character string included in a captured image in which recognition of a character string based on a first algorithm has failed, a display screen image based at least on the captured image displayed on a display screen of the input device. The communication interface acquires the captured image from the image acquisition device. The processor searches the captured image corresponding to the display screen image to acquire a character string based on a result of character recognition processing executed on the searched captured image on the basis of a second algorithm different from the first algorithm, and inputs the character string to the input device through the input interface.

Description

情報処理装置、システム及び制御方法Information processing equipment, system and control method
 本発明の実施形態は、情報処理装置、システム及び制御方法に関する。 An embodiment of the present invention relates to an information processing device, a system, and a control method.
 OCR(optical character recognition)処理により住所などの文字列を読み取る認識装置と、認識装置が文字列の認識に失敗した場合にオペレータから文字列の入力を受け付けるVCS(video coding system)とを備える認識システムが提供されている。 A recognition system equipped with a recognition device that reads character strings such as addresses by OCR (optical character recognition) processing, and a VCS (video coding system) that accepts character string input from the operator when the recognition device fails to recognize the character string. Is provided.
 そのような認識システムでは、文字列の認識精度を向上させるためには認識装置を改変する必要がある。 In such a recognition system, it is necessary to modify the recognition device in order to improve the recognition accuracy of the character string.
 そこで、既存の認識システムを改変することなく、効果的に文字列を取得する技術が望まれている。 Therefore, a technique for effectively acquiring a character string without modifying the existing recognition system is desired.
日本国特開2005-007315号公報Japanese Patent Application Laid-Open No. 2005-007315
 上記の課題を解決するため、効果的に文字列を取得することができる情報処理装置、システム及び制御方法を提供する。 In order to solve the above problems, an information processing device, a system and a control method capable of effectively acquiring a character string are provided.
 実施形態によれば、情報処理装置は、画像インターフェースと、入力インターフェースと、通信インターフェースと、プロセッサと、を備える。画像インターフェースは、第1のアルゴリズムによる文字列の認識に失敗した撮像画像に含まれる文字列を入力するための入力装置から前記入力装置の表示画面に表示される少なくとも前記撮像画像に基づく表示画面画像を取得する。入力インターフェースは、前記入力装置に文字列を入力する。通信インターフェースは、画像取得装置からの前記撮像画像を取得する。プロセッサは、前記表示画面画像に対応する前記撮像画像を探索し、前記第1のアルゴリズムと異なる第2のアルゴリズムによる、探索された前記撮像画像の文字認識処理の結果に基づく文字列を取得し、前記入力インターフェースを通じて、前記文字列を前記入力装置に入力する。 According to the embodiment, the information processing device includes an image interface, an input interface, a communication interface, and a processor. The image interface is a display screen image based on at least the captured image displayed on the display screen of the input device from the input device for inputting the character string included in the captured image in which the recognition of the character string by the first algorithm fails. To get. The input interface inputs a character string into the input device. The communication interface acquires the captured image from the image acquisition device. The processor searches for the captured image corresponding to the display screen image, acquires a character string based on the result of character recognition processing of the searched captured image by a second algorithm different from the first algorithm, and obtains a character string. The character string is input to the input device through the input interface.
図1は、実施形態に係る認識システムの構成例を示すブロック図である。FIG. 1 is a block diagram showing a configuration example of a recognition system according to an embodiment. 図2は、実施形態に係る第1の認識装置の構成例を示すブロック図である。FIG. 2 is a block diagram showing a configuration example of the first recognition device according to the embodiment. 図3は、実施形態に係るVCSの構成例を示すブロック図である。FIG. 3 is a block diagram showing a configuration example of the VCS according to the embodiment. 図4は、実施形態に係るマッチング装置の構成例を示すブロック図である。FIG. 4 is a block diagram showing a configuration example of the matching device according to the embodiment. 図5は、実施形態に係る第2の認識装置の構成例を示すブロック図である。FIG. 5 is a block diagram showing a configuration example of the second recognition device according to the embodiment. 図6は、実施形態に係る入力画面の例を示す図である。FIG. 6 is a diagram showing an example of an input screen according to the embodiment. 図7は、実施形態に係る第1の認識装置の動作例を示すフローチャートである。FIG. 7 is a flowchart showing an operation example of the first recognition device according to the embodiment. 図8は、実施形態に係るVCSの動作例を示すフローチャートである。FIG. 8 is a flowchart showing an operation example of the VCS according to the embodiment. 図9は、実施形態に係る第2の認識装置の動作例を示すフローチャートである。FIG. 9 is a flowchart showing an operation example of the second recognition device according to the embodiment. 図10は、実施形態に係る第2の認識装置の動作例を示すフローチャートである。FIG. 10 is a flowchart showing an operation example of the second recognition device according to the embodiment. 図11は、実施形態に係るマッチング装置の動作例を示すフローチャートである。FIG. 11 is a flowchart showing an operation example of the matching device according to the embodiment.
実施形態Embodiment
 以下、実施形態について、図面を参照して説明する。 
 実施形態に係る認識システムは、ソータに投入される物品から住所などの宛先を読み取る。認識システムは、読み取った宛先に基づいて物品の仕分先(たとえば、ソータのシュート)を設定する。認識システムは、宛先の読み取りに失敗した場合、宛先を目視したオペレータから宛先の入力を受け付ける。
Hereinafter, embodiments will be described with reference to the drawings.
The recognition system according to the embodiment reads a destination such as an address from an article put into the sorter. The recognition system sets the destination of the article (eg, sorter shoot) based on the read destination. When the recognition system fails to read the destination, the recognition system accepts the input of the destination from the operator who visually checks the destination.
 図1は、実施形態に係る認識システム1の構成例を示す。図1が示すように、認識システム1は、ソータ2、カメラ3、第1の認識装置10、VCS20(20a乃至20d)、マッチング装置30(30a乃至30d)、操作部40(40a及び40b)、表示部50(50a及び50b)及び第2の認識装置60などを備える。 FIG. 1 shows a configuration example of the recognition system 1 according to the embodiment. As shown in FIG. 1, the recognition system 1 includes a sorter 2, a camera 3, a first recognition device 10, a VCS 20 (20a to 20d), a matching device 30 (30a to 30d), and an operation unit 40 (40a and 40b). A display unit 50 (50a and 50b), a second recognition device 60, and the like are provided.
 第1の認識装置10は、ソータ2、カメラ3及びVCS20に接続する。VCS20a乃至20dは、マッチング装置30a乃至30dにそれぞれ接続する。マッチング装置30a及び30bは、操作部40a及び40bにそれぞれ接続する。また、マッチング装置30a及び30bは、表示部50a及び50bにそれぞれ接続する。第2の認識装置60は、カメラ3及びマッチング装置30に接続する。 The first recognition device 10 is connected to the sorter 2, the camera 3, and the VCS 20. The VCSs 20a to 20d are connected to the matching devices 30a to 30d, respectively. The matching devices 30a and 30b are connected to the operation units 40a and 40b, respectively. Further, the matching devices 30a and 30b are connected to the display units 50a and 50b, respectively. The second recognition device 60 is connected to the camera 3 and the matching device 30.
 なお、認識システム1は、図1が示すような構成の他に必要に応じた構成をさらに具備したり、認識システム1から特定の構成が除外されたりしてもよい。 Note that the recognition system 1 may further include a configuration as required in addition to the configuration shown in FIG. 1, or a specific configuration may be excluded from the recognition system 1.
 ソータ2は、第1の認識装置10からの信号に基づいて、投入される物品を仕分先に区分する。たとえば、ソータ2は、仕分先として複数のシュートを備える。ソータ2は、第1の認識装置10からの信号に基づいて、物品をシュートに投入する。たとえば、ソータ2は、物品を特定するIDと当該物品を投入する仕分先(たとえば、シュートの番号など)とを示す仕分情報を第1の認識装置10から取得する。ソータ2は、仕分情報に基づいて物品をシュートに投入する。 The sorter 2 classifies the items to be input into the suppliers based on the signal from the first recognition device 10. For example, the sorter 2 includes a plurality of shoots as a partition. The sorter 2 puts the article into the chute based on the signal from the first recognition device 10. For example, the sorter 2 acquires assortment information indicating an ID for identifying an article and a supplier (for example, a chute number) for inserting the article from the first recognition device 10. The sorter 2 puts an article into the chute based on the sorting information.
 カメラ3(画像取得装置)は、ソータ2に投入される物品を撮像する。カメラ3は、物品の宛先が記載されている面(宛先面)を撮像する。たとえば、カメラ3は、ソータ2に物品を投入する搬送路上に設置されている。カメラ3は、物品を複数の面から撮像するものであってもよい。カメラ3は、撮像した画像を第1の認識装置10及び第2の認識装置60に送信する。 The camera 3 (image acquisition device) captures an article to be put into the sorter 2. The camera 3 captures a surface (destination surface) on which the destination of the article is described. For example, the camera 3 is installed on a transport path for loading articles into the sorter 2. The camera 3 may capture an article from a plurality of surfaces. The camera 3 transmits the captured image to the first recognition device 10 and the second recognition device 60.
 第1の認識装置10は、カメラ3から画像(撮像画像)などに基づいてソータ2に物品の仕分先を設定する。たとえば、第1の認識装置10は、物品を識別するIDと当該物品を投入する仕分先とを示す仕分情報をソータ2に送信する。第1の認識装置10については、後に詳述する。 The first recognition device 10 sets the sort destination of the article in the sorter 2 based on an image (captured image) or the like from the camera 3. For example, the first recognition device 10 transmits to the sorter 2 the sorting information indicating the ID for identifying the article and the partition to which the article is put. The first recognition device 10 will be described in detail later.
 VCS20は、第1の認識装置10が宛先の認識に失敗した場合に、宛先の認識に失敗した撮像画像(宛先面の撮像画像)に含まれる宛先を入力するための入力装置である。VCS20については、後に詳述する。 The VCS20 is an input device for inputting a destination included in the captured image (captured image of the destination surface) in which the recognition of the destination fails when the first recognition device 10 fails to recognize the destination. VCS20 will be described in detail later.
 マッチング装置30(情報処理装置)は、第2の認識装置60からの宛先をVCS20に入力する。マッチング装置30については、後に詳述する。 The matching device 30 (information processing device) inputs the destination from the second recognition device 60 to the VCS 20. The matching device 30 will be described in detail later.
 操作部40は、オペレータから種々の操作の入力を受け付ける。操作部40は、入力された操作を示す信号をマッチング装置30へ送信する。操作部40は、キーボード、ボタン又はタッチパネルなどから構成される。 The operation unit 40 receives inputs for various operations from the operator. The operation unit 40 transmits a signal indicating the input operation to the matching device 30. The operation unit 40 is composed of a keyboard, buttons, a touch panel, and the like.
 表示部50は、マッチング装置30からの制御に基づいて情報を表示する。たとえば、表示部50は、液晶モニタから構成される。操作部40がタッチパネルから構成される場合、表示部50は、操作部40と一体的に形成された液晶モニタから構成される。 The display unit 50 displays information based on the control from the matching device 30. For example, the display unit 50 is composed of a liquid crystal monitor. When the operation unit 40 is composed of a touch panel, the display unit 50 is composed of a liquid crystal monitor integrally formed with the operation unit 40.
 なお、認識システム1は、マッチング装置30c及び30dにそれぞれ接続する操作部及び表示部を備えるものであってもよい。 The recognition system 1 may include an operation unit and a display unit connected to the matching devices 30c and 30d, respectively.
 第2の認識装置60は、OCR処理(文字認識処理)により、撮像画像から宛先を認識する。第2の認識装置60は、撮像画像と認識した宛先とをマッチング装置30に送信する。 The second recognition device 60 recognizes the destination from the captured image by OCR processing (character recognition processing). The second recognition device 60 transmits the captured image and the recognized destination to the matching device 30.
 次に、第1の認識装置10について説明する。 
 図2は、第1の認識装置10の構成例を示す。図2が示すように、第1の認識装置10は、プロセッサ11、メモリ12、操作部13、表示部14、カメラインターフェース15及び通信インターフェース16などを備える。プロセッサ11と、メモリ12、操作部13、表示部14、カメラインターフェース15及び通信インターフェース16と、は、データバス又は所定のインターフェースなどを介して通信可能に接続する。
Next, the first recognition device 10 will be described.
FIG. 2 shows a configuration example of the first recognition device 10. As shown in FIG. 2, the first recognition device 10 includes a processor 11, a memory 12, an operation unit 13, a display unit 14, a camera interface 15, a communication interface 16, and the like. The processor 11 and the memory 12, the operation unit 13, the display unit 14, the camera interface 15, and the communication interface 16 are communicably connected to each other via a data bus, a predetermined interface, or the like.
 なお、第1の認識装置10は、図2が示すような構成の他に必要に応じた構成をさらに具備したり、第1の認識装置10から特定の構成が除外されたりしてもよい。 Note that the first recognition device 10 may further include a configuration as required in addition to the configuration as shown in FIG. 2, or a specific configuration may be excluded from the first recognition device 10.
 プロセッサ11は、第1の認識装置10全体の動作を制御する。たとえば、プロセッサ11は、宛先の認識結果などに基づいて仕分情報を生成し、ソータ2に送信する。 The processor 11 controls the operation of the first recognition device 10 as a whole. For example, the processor 11 generates sorting information based on the recognition result of the destination and transmits it to the sorter 2.
 たとえば、プロセッサ11は、CPUなどから構成される。また、プロセッサ11は、ASIC(Application Specific Integrated Circuit)などから構成されるものであってもよい。また、プロセッサ11は、FPGA(Field Programmable Gate Array)などから構成されるものであってもよい。 For example, the processor 11 is composed of a CPU and the like. Further, the processor 11 may be composed of an ASIC (Application Specific Integrated Circuit) or the like. Further, the processor 11 may be composed of an FPGA (Field Programmable Gate Array) or the like.
 メモリ12は、種々のデータを格納する。たとえば、メモリ12は、ROM、RAM及びNVMとして機能する。 
 たとえば、メモリ12は、制御プログラム及び制御データなどを記憶する。制御プログラム及び制御データは、第1の認識装置10の仕様に応じて予め組み込まれる。たとえば、制御プログラムは、第1の認識装置10で実現する機能をサポートするプログラムなどである。
The memory 12 stores various data. For example, the memory 12 functions as a ROM, RAM and NVM.
For example, the memory 12 stores a control program, control data, and the like. The control program and control data are preliminarily incorporated according to the specifications of the first recognition device 10. For example, the control program is a program that supports the functions realized by the first recognition device 10.
 また、メモリ12は、プロセッサ11の処理中のデータなどを一時的に格納する。また、メモリ12は、アプリケーションプログラムの実行に必要なデータ及びアプリケーションプログラムの実行結果などを格納してもよい。 In addition, the memory 12 temporarily stores data and the like being processed by the processor 11. Further, the memory 12 may store data necessary for executing the application program, an execution result of the application program, and the like.
 操作部13は、オペレータから種々の操作の入力を受け付ける。操作部13は、入力された操作を示す信号をプロセッサ11へ送信する。操作部13は、キーボード、ボタン又はタッチパネルなどから構成される。 The operation unit 13 receives inputs for various operations from the operator. The operation unit 13 transmits a signal indicating the input operation to the processor 11. The operation unit 13 is composed of a keyboard, buttons, a touch panel, and the like.
 表示部14は、プロセッサ11からの制御に基づいて情報を表示する。たとえば、表示部14は、液晶モニタから構成される。操作部13がタッチパネルから構成される場合、表示部14は、操作部13と一体的に形成された液晶モニタから構成される。 The display unit 14 displays information based on the control from the processor 11. For example, the display unit 14 is composed of a liquid crystal monitor. When the operation unit 13 is composed of a touch panel, the display unit 14 is composed of a liquid crystal monitor integrally formed with the operation unit 13.
 カメラインターフェース15は、カメラ3とデータを送受信するためのインターフェースである。例えば、カメラインターフェース15は、有線でカメラ3と接続する。カメラインターフェース15は、カメラ3からの撮像画像を受信する。カメラインターフェース15は、受信した撮像画像をプロセッサ11に送信する。また、カメラインターフェース15は、カメラ3に電力を供給するものであってもよい。 The camera interface 15 is an interface for transmitting and receiving data to and from the camera 3. For example, the camera interface 15 is connected to the camera 3 by wire. The camera interface 15 receives the captured image from the camera 3. The camera interface 15 transmits the received captured image to the processor 11. Further, the camera interface 15 may supply electric power to the camera 3.
 通信インターフェース16は、ソータ2及びVCS20とデータを送受信するためのインターフェースである。たとえば、通信インターフェース16は、LAN(Local Area Network)接続をサポートするものである。また、たとえば、通信インターフェース16は、USB(Universal Serial Bus)接続をサポートするものであってもよい。なお、通信インターフェース16は、第1の認識装置10とデータを送受信するためのインターフェースと、VCS20とデータを送受信するためのインターフェースと、から構成されてもよい。 The communication interface 16 is an interface for transmitting and receiving data to and from the sorter 2 and the VCS 20. For example, the communication interface 16 supports a LAN (Local Area Network) connection. Further, for example, the communication interface 16 may support a USB (Universal Serial Bus) connection. The communication interface 16 may be composed of an interface for transmitting and receiving data with the first recognition device 10 and an interface for transmitting and receiving data with the VCS 20.
 次に、VCS20について説明する。 
 VCS20a乃至20dは、同様の構成であるため、VCS20として説明する。
Next, the VCS 20 will be described.
Since VCS20a to 20d have the same configuration, they will be described as VCS20.
 図3は、VCS20の構成例を示す。図3が示すように、VCS20は、プロセッサ21、メモリ22、操作部インターフェース23、表示部インターフェース24及び通信インターフェース25などを備える。プロセッサ21と、メモリ22、操作部インターフェース23、表示部インターフェース24及び通信インターフェース25と、は、データバス又は所定のインターフェースなどを介して通信可能に接続する。 FIG. 3 shows a configuration example of VCS20. As shown in FIG. 3, the VCS 20 includes a processor 21, a memory 22, an operation unit interface 23, a display unit interface 24, a communication interface 25, and the like. The processor 21, the memory 22, the operation unit interface 23, the display unit interface 24, and the communication interface 25 are communicably connected to each other via a data bus, a predetermined interface, or the like.
 なお、VCS20は、図3が示すような構成の他に必要に応じた構成をさらに具備したり、VCS20から特定の構成が除外されたりしてもよい。 In addition to the configuration shown in FIG. 3, the VCS 20 may further include a configuration as required, or a specific configuration may be excluded from the VCS 20.
 プロセッサ21は、VCS20全体の動作を制御する。たとえば、プロセッサ21は、表示部インターフェース24を通じて、宛先の認識に失敗した撮像画像を出力する。 The processor 21 controls the operation of the entire VCS20. For example, the processor 21 outputs a captured image that fails to recognize the destination through the display unit interface 24.
 たとえば、プロセッサ21は、CPUなどから構成される。また、プロセッサ21は、ASICなどから構成されるものであってもよい。また、プロセッサ21は、FPGAなどから構成されるものであってもよい。 For example, the processor 21 is composed of a CPU and the like. Further, the processor 21 may be composed of an ASIC or the like. Further, the processor 21 may be composed of an FPGA or the like.
 メモリ22は、種々のデータを格納する。たとえば、メモリ22は、ROM、RAM及びNVMとして機能する。 
 たとえば、メモリ22は、制御プログラム及び制御データなどを記憶する。制御プログラム及び制御データは、VCS20の仕様に応じて予め組み込まれる。たとえば、制御プログラムは、VCS20で実現する機能をサポートするプログラムなどである。
The memory 22 stores various data. For example, the memory 22 functions as a ROM, RAM and NVM.
For example, the memory 22 stores a control program, control data, and the like. The control program and control data are preliminarily incorporated according to the specifications of the VCS20. For example, the control program is a program that supports the functions realized by the VCS20.
 また、メモリ22は、プロセッサ21の処理中のデータなどを一時的に格納する。また、メモリ22は、アプリケーションプログラムの実行に必要なデータ及びアプリケーションプログラムの実行結果などを格納してもよい。 In addition, the memory 22 temporarily stores data and the like being processed by the processor 21. Further, the memory 22 may store data necessary for executing the application program, an execution result of the application program, and the like.
 操作部インターフェース23は、操作の入力を受け付ける入力装置とデータを送受信するためのインターフェースである。たとえば、操作部インターフェース23は、キーボードに入力される操作(キー入力操作)を示す操作信号を入力装置から受信する。操作部インターフェース23は、受信した操作信号をプロセッサ21に送信する。また、操作部インターフェース23は、入力装置に電力を供給するものであってもよい。たとえば、操作部インターフェース23は、USB接続をサポートする。 The operation unit interface 23 is an interface for transmitting and receiving data to and from an input device that receives input for operations. For example, the operation unit interface 23 receives an operation signal indicating an operation (key input operation) input to the keyboard from the input device. The operation unit interface 23 transmits the received operation signal to the processor 21. Further, the operation unit interface 23 may supply electric power to the input device. For example, the operating unit interface 23 supports a USB connection.
 表示部インターフェース24は、画像を表示する表示装置とデータを送受信するためのインターフェースである。表示部インターフェース24は、プロセッサ21からの画像データを表示装置に出力する。 The display unit interface 24 is an interface for transmitting and receiving data to and from a display device that displays an image. The display unit interface 24 outputs the image data from the processor 21 to the display device.
 通信インターフェース25は、第1の認識装置10及びマッチング装置30とデータを送受信するためのインターフェースである。たとえば、通信インターフェース25は、LAN接続をサポートするものである。また、たとえば、通信インターフェース25は、USB接続をサポートするものであってもよい。なお、通信インターフェース25は、第1の認識装置10とデータを送受信するためのインターフェースと、マッチング装置30とデータを送受信するためのインターフェースと、から構成されてもよい。 The communication interface 25 is an interface for transmitting and receiving data to and from the first recognition device 10 and the matching device 30. For example, the communication interface 25 supports a LAN connection. Further, for example, the communication interface 25 may support a USB connection. The communication interface 25 may be composed of an interface for transmitting and receiving data with the first recognition device 10 and an interface for transmitting and receiving data with the matching device 30.
 次に、マッチング装置30について説明する。 
 マッチング装置30a乃至30dは、同様の構成であるため、マッチング装置30として説明する。
Next, the matching device 30 will be described.
Since the matching devices 30a to 30d have the same configuration, they will be described as the matching device 30.
 図4は、マッチング装置30の構成例を示す。図4が示すように、マッチング装置30は、プロセッサ31、メモリ32、画像インターフェース33、入力インターフェース34、操作部インターフェース35、表示部インターフェース36及び通信インターフェース37などを備える。プロセッサ31と、メモリ32、画像インターフェース33、入力インターフェース34、操作部インターフェース35、表示部インターフェース36及び通信インターフェース37と、は、データバス又は所定のインターフェースなどを介して通信可能に接続する。 FIG. 4 shows a configuration example of the matching device 30. As shown in FIG. 4, the matching device 30 includes a processor 31, a memory 32, an image interface 33, an input interface 34, an operation unit interface 35, a display unit interface 36, a communication interface 37, and the like. The processor 31 and the memory 32, the image interface 33, the input interface 34, the operation unit interface 35, the display unit interface 36, and the communication interface 37 are communicably connected to each other via a data bus or a predetermined interface.
 なお、マッチング装置30は、図4が示すような構成の他に必要に応じた構成をさらに具備したり、マッチング装置30から特定の構成が除外されたりしてもよい。 In addition to the configuration shown in FIG. 4, the matching device 30 may further include a configuration as required, or a specific configuration may be excluded from the matching device 30.
 プロセッサ31(第2のプロセッサ)は、マッチング装置30全体の動作を制御する。たとえば、プロセッサ31は、第2の認識装置60からの宛先をVCS20に入力する。 The processor 31 (second processor) controls the operation of the entire matching device 30. For example, the processor 31 inputs the destination from the second recognition device 60 to the VCS 20.
 たとえば、プロセッサ31は、CPUなどから構成される。また、プロセッサ31は、ASICなどから構成されるものであってもよい。また、プロセッサ31は、FPGAなどから構成されるものであってもよい。 For example, the processor 31 is composed of a CPU and the like. Further, the processor 31 may be composed of an ASIC or the like. Further, the processor 31 may be composed of an FPGA or the like.
 メモリ32は、種々のデータを格納する。たとえば、メモリ32は、ROM、RAM及びNVMとして機能する。 
 たとえば、メモリ32は、制御プログラム及び制御データなどを記憶する。制御プログラム及び制御データは、マッチング装置30の仕様に応じて予め組み込まれる。たとえば、制御プログラムは、マッチング装置30で実現する機能をサポートするプログラムなどである。
The memory 32 stores various data. For example, the memory 32 functions as a ROM, RAM and NVM.
For example, the memory 32 stores a control program, control data, and the like. The control program and control data are preliminarily incorporated according to the specifications of the matching device 30. For example, the control program is a program that supports the functions realized by the matching device 30.
 また、メモリ32は、プロセッサ31の処理中のデータなどを一時的に格納する。また、メモリ32は、アプリケーションプログラムの実行に必要なデータ及びアプリケーションプログラムの実行結果などを格納してもよい。 In addition, the memory 32 temporarily stores data and the like being processed by the processor 31. Further, the memory 32 may store data necessary for executing the application program, an execution result of the application program, and the like.
 画像インターフェース33は、VCS20の表示部インターフェース24に接続する。画像インターフェース33は、表示部インターフェース24から画像を取得する。即ち、画像インターフェース33は、VCS20のプロセッサ21が表示装置に表示しようとする画像を取得する。画像インターフェース33は、取得した画像をプロセッサ31に送信する。たとえば、画像インターフェース33は、キャプチャボードなどから構成される。 The image interface 33 is connected to the display interface 24 of the VCS 20. The image interface 33 acquires an image from the display interface 24. That is, the image interface 33 acquires an image that the processor 21 of the VCS 20 intends to display on the display device. The image interface 33 transmits the acquired image to the processor 31. For example, the image interface 33 is composed of a capture board or the like.
 入力インターフェース34は、操作部インターフェース23に接続する。入力インターフェース34は、プロセッサ31からの制御に従って操作部インターフェース23にキー入力操作を示す操作信号を入力する。たとえば、入力インターフェース34は、USB接続をサポートする。 The input interface 34 is connected to the operation unit interface 23. The input interface 34 inputs an operation signal indicating a key input operation to the operation unit interface 23 according to the control from the processor 31. For example, the input interface 34 supports a USB connection.
 操作部インターフェース35は、操作部40とデータを送受信するためのインターフェースである。たとえば、操作部インターフェース35は、操作部40に入力された操作を示す操作信号を操作部40から受信する。操作部インターフェース35は、受信した操作信号をプロセッサ31に送信する。また、操作部インターフェース35は、操作部40に電力を供給するものであってもよい。たとえば、操作部インターフェース35は、USB接続をサポートする。 The operation unit interface 35 is an interface for transmitting and receiving data to and from the operation unit 40. For example, the operation unit interface 35 receives an operation signal indicating an operation input to the operation unit 40 from the operation unit 40. The operation unit interface 35 transmits the received operation signal to the processor 31. Further, the operation unit interface 35 may supply electric power to the operation unit 40. For example, the operating unit interface 35 supports a USB connection.
 表示部インターフェース36は、表示部50とデータを送受信するためのインターフェースである。表示部インターフェース36は、プロセッサ31からの画像データを表示部50に出力する。 The display unit interface 36 is an interface for transmitting and receiving data to and from the display unit 50. The display unit interface 36 outputs the image data from the processor 31 to the display unit 50.
 通信インターフェース37(第2の通信インターフェース)は、VCS20、他のマッチング装置30及び第2の認識装置60とデータを送受信するためのインターフェースである。たとえば、通信インターフェース37は、LAN接続をサポートするものである。また、たとえば、通信インターフェース37は、USB接続をサポートするものであってもよい。なお、通信インターフェース37は、VCS20とデータを送受信するためのインターフェースと、他のマッチング装置30とデータを送受信するためのインターフェースと、第2の認識装置60とデータを送受信するためのインターフェースと、から構成されてもよい。 The communication interface 37 (second communication interface) is an interface for transmitting and receiving data to and from the VCS20, another matching device 30, and the second recognition device 60. For example, the communication interface 37 supports a LAN connection. Further, for example, the communication interface 37 may support a USB connection. The communication interface 37 is composed of an interface for transmitting and receiving data to and from the VCS 20, an interface for transmitting and receiving data to and from the other matching device 30, and an interface for transmitting and receiving data to and from the second recognition device 60. It may be configured.
 なお、マッチング装置30c及び30dは、操作部インターフェース35及び表示部インターフェース36を備えなくともよい。 Note that the matching devices 30c and 30d do not have to include the operation unit interface 35 and the display unit interface 36.
 次に、第2の認識装置60について説明する。 
 図5は、第2の認識装置60の構成例を示す。図5が示すように、第2の認識装置60は、プロセッサ61、メモリ62、操作部63、表示部64、カメラインターフェース65及び通信インターフェース66などを備える。プロセッサ61と、メモリ62、操作部63、表示部64、カメラインターフェース65及び通信インターフェース66と、は、データバス又は所定のインターフェースなどを介して通信可能に接続する。
Next, the second recognition device 60 will be described.
FIG. 5 shows a configuration example of the second recognition device 60. As shown in FIG. 5, the second recognition device 60 includes a processor 61, a memory 62, an operation unit 63, a display unit 64, a camera interface 65, a communication interface 66, and the like. The processor 61, the memory 62, the operation unit 63, the display unit 64, the camera interface 65, and the communication interface 66 are communicably connected to each other via a data bus, a predetermined interface, or the like.
 なお、第2の認識装置60は、図2が示すような構成の他に必要に応じた構成をさらに具備したり、第2の認識装置60から特定の構成が除外されたりしてもよい。 The second recognition device 60 may further include a configuration as required in addition to the configuration as shown in FIG. 2, or a specific configuration may be excluded from the second recognition device 60.
 プロセッサ61(第1のプロセッサ)は、第2の認識装置60全体の動作を制御する。たとえば、プロセッサ61は、撮像画像から宛先を取得する。 The processor 61 (first processor) controls the operation of the entire second recognition device 60. For example, the processor 61 acquires a destination from a captured image.
 たとえば、プロセッサ61は、CPUなどから構成される。また、プロセッサ61は、ASIC(Application Specific Integrated Circuit)などから構成されるものであってもよい。また、プロセッサ61は、FPGA(Field Programmable Gate Array)などから構成されるものであってもよい。 For example, the processor 61 is composed of a CPU and the like. Further, the processor 61 may be composed of an ASIC (Application Specific Integrated Circuit) or the like. Further, the processor 61 may be composed of an FPGA (Field Programmable Gate Array) or the like.
 メモリ62は、種々のデータを格納する。たとえば、メモリ62は、ROM、RAM及びNVMとして機能する。 
 たとえば、メモリ62は、制御プログラム及び制御データなどを記憶する。制御プログラム及び制御データは、第2の認識装置60の仕様に応じて予め組み込まれる。たとえば、制御プログラムは、第2の認識装置60で実現する機能をサポートするプログラムなどである。
The memory 62 stores various data. For example, the memory 62 functions as a ROM, RAM and NVM.
For example, the memory 62 stores a control program, control data, and the like. The control program and control data are preliminarily incorporated according to the specifications of the second recognition device 60. For example, the control program is a program that supports the functions realized by the second recognition device 60.
 また、メモリ62は、プロセッサ61の処理中のデータなどを一時的に格納する。また、メモリ62は、アプリケーションプログラムの実行に必要なデータ及びアプリケーションプログラムの実行結果などを格納してもよい。 Further, the memory 62 temporarily stores data and the like being processed by the processor 61. Further, the memory 62 may store data necessary for executing the application program, an execution result of the application program, and the like.
 操作部63は、オペレータから種々の操作の入力を受け付ける。操作部63は、入力された操作を示す信号をプロセッサ61へ送信する。操作部63は、キーボード、ボタン又はタッチパネルなどから構成される。 The operation unit 63 receives inputs for various operations from the operator. The operation unit 63 transmits a signal indicating the input operation to the processor 61. The operation unit 63 includes a keyboard, buttons, a touch panel, and the like.
 表示部64は、プロセッサ61からの制御に基づいて情報を表示する。たとえば、表示部64は、液晶モニタから構成される。操作部63がタッチパネルから構成される場合、表示部64は、操作部63と一体的に形成された液晶モニタから構成される。 The display unit 64 displays information based on the control from the processor 61. For example, the display unit 64 is composed of a liquid crystal monitor. When the operation unit 63 is composed of a touch panel, the display unit 64 is composed of a liquid crystal monitor integrally formed with the operation unit 63.
 カメラインターフェース65(画像取得装置インターフェース)は、カメラ3とデータを送受信するためのインターフェースである。例えば、カメラインターフェース65は、有線でカメラ3と接続する。カメラインターフェース65は、カメラ3からの撮像画像を受信する。カメラインターフェース65は、受信した撮像画像をプロセッサ61に送信する。 The camera interface 65 (image acquisition device interface) is an interface for transmitting and receiving data to and from the camera 3. For example, the camera interface 65 is connected to the camera 3 by wire. The camera interface 65 receives the captured image from the camera 3. The camera interface 65 transmits the received captured image to the processor 61.
 通信インターフェース66(第1の通信インターフェース)は、マッチング装置30とデータを送受信するためのインターフェースである。たとえば、通信インターフェース66は、LAN接続をサポートするものである。また、たとえば、通信インターフェース66は、USB接続をサポートするものであってもよい。 The communication interface 66 (first communication interface) is an interface for transmitting and receiving data to and from the matching device 30. For example, the communication interface 66 supports a LAN connection. Further, for example, the communication interface 66 may support a USB connection.
 次に、第1の認識装置10が実現する機能について説明する。第1の認識装置10が実現する機能は、プロセッサ11がメモリ12などに格納されるプログラムを実行することで実現される。 Next, the functions realized by the first recognition device 10 will be described. The function realized by the first recognition device 10 is realized by the processor 11 executing a program stored in the memory 12 or the like.
 まず、プロセッサ11は、カメラ3から宛先面を含む撮像画像を取得する機能を有する。 First, the processor 11 has a function of acquiring an captured image including a destination surface from the camera 3.
 ここで、カメラ3は、物品がカメラ3の撮像領域を通過するタイミングで画像を撮像する。カメラ3は、撮像した画像を第1の認識装置10に送信する。 Here, the camera 3 captures an image at the timing when the article passes through the imaging region of the camera 3. The camera 3 transmits the captured image to the first recognition device 10.
 プロセッサ11は、カメラインターフェース15を通じてカメラ3から宛先面を含む撮像画像を取得する。なお、プロセッサ11は、カメラ3にリクエストを送信して、撮像画像を含むレスポンスを受信してもよい。 The processor 11 acquires an captured image including the destination surface from the camera 3 through the camera interface 15. The processor 11 may send a request to the camera 3 and receive a response including the captured image.
 また、プロセッサ11は、OCR処理により撮像画像から宛先を取得する機能を有する。 Further, the processor 11 has a function of acquiring a destination from the captured image by OCR processing.
 撮像画像を取得すると、プロセッサ11は、所定のアルゴリズム(第1のアルゴリズム)に従って撮像画像にOCR処理を行う。OCR処理を行うと、プロセッサ11は、OCR処理の結果に基づいて物品の宛先面に記載されている宛先を取得する。 When the captured image is acquired, the processor 11 performs OCR processing on the captured image according to a predetermined algorithm (first algorithm). When the OCR process is performed, the processor 11 acquires the destination described on the destination surface of the article based on the result of the OCR process.
 また、プロセッサ11は、OCR処理に失敗した場合、VCS20を用いて宛先を取得する機能を有する。 Further, the processor 11 has a function of acquiring a destination by using the VCS20 when the OCR process fails.
 OCR処理に失敗して宛先を取得できない場合、プロセッサ11は、通信インターフェース16を通じて撮像画像をVCS20に送信する。プロセッサ11は、VCS20a乃至20dから1つのVCS20を選択し、選択されたVCS20に撮像画像を送信する。 If the OCR process fails and the destination cannot be acquired, the processor 11 transmits the captured image to the VCS 20 through the communication interface 16. The processor 11 selects one VCS20 from the VCSs 20a to 20d, and transmits the captured image to the selected VCS20.
 後述するように、VCS20は、撮像画像に含まれる宛先面に記載された宛先を第1の認識装置10に送信する。 
 プロセッサ11は、通信インターフェース16を通じてVCS20から宛先を取得する。
As will be described later, the VCS 20 transmits the destination described on the destination surface included in the captured image to the first recognition device 10.
The processor 11 acquires a destination from the VCS 20 through the communication interface 16.
 プロセッサ11は、OCR処理によって取得した宛先又はVCS20からの宛先に基づいて物品の仕分先を設定する機能を有する。 The processor 11 has a function of setting a supplier of articles based on a destination acquired by OCR processing or a destination from VCS20.
 たとえば、プロセッサ11は、宛先に基づいて仕分先としてソータ2において物品が投入されるシュートの番号を設定する。たとえば、プロセッサ11は、宛先の行政区画(都道府県又は市町村など)に対応するシュートの番号を設定する。 For example, the processor 11 sets the number of the chute into which the article is inserted in the sorter 2 as the supplier based on the destination. For example, the processor 11 sets the number of the shoot corresponding to the destination administrative division (prefecture, municipality, etc.).
 プロセッサ11は、通信インターフェース16を通じて、物品を特定するIDと当該物品の仕分先とを示す仕分情報をソータ2に送信する。 The processor 11 transmits the sorting information indicating the ID for identifying the article and the sorting destination of the article to the sorter 2 through the communication interface 16.
 次に、VCS20が実現する機能について説明する。VCS20が実現する機能は、プロセッサ21がメモリ22などに格納されるプログラムを実行することで実現される。 Next, the functions realized by VCS20 will be described. The function realized by the VCS 20 is realized by the processor 21 executing a program stored in the memory 22 or the like.
 まず、プロセッサ21は、第1の認識装置10から宛先面を含む撮像画像を取得する機能を有する。 First, the processor 21 has a function of acquiring an captured image including a destination surface from the first recognition device 10.
 前述の通り、第1の認識装置10のプロセッサ11は、OCR処理に失敗すると、撮像画像をVCS20に送信する。 As described above, the processor 11 of the first recognition device 10 transmits the captured image to the VCS 20 when the OCR process fails.
 VCS20のプロセッサ21は、通信インターフェース25を通じて第1の認識装置10から撮像画像を取得する。 The processor 21 of the VCS 20 acquires the captured image from the first recognition device 10 through the communication interface 25.
 また、プロセッサ21は、取得した撮像画像をマッチング装置30へ送信する機能を有する。 Further, the processor 21 has a function of transmitting the acquired captured image to the matching device 30.
 撮像画像を取得すると、プロセッサ21は、撮像画像に写る宛先の入力を受け付ける入力画面(表示画面)を生成する。入力画面は、取得された撮像画像を含む。 When the captured image is acquired, the processor 21 generates an input screen (display screen) that accepts the input of the destination reflected in the captured image. The input screen includes the acquired captured image.
 図6は、プロセッサ21が生成した入力画面100の例を示す。図6が示すように、入力画面100は、画像領域101及び入力欄102などを備える。 FIG. 6 shows an example of the input screen 100 generated by the processor 21. As shown in FIG. 6, the input screen 100 includes an image area 101, an input field 102, and the like.
 画像領域101は、第1の認識装置10から取得された撮像画像(表示画面画像)を表示する。画像領域101は、宛先面を含む撮像画像を表示する。なお、画像領域101が表示する撮像画像に含まれる文字列の画像解像度は、カメラ3が撮像した撮像画像に含まれる文字列の画像解像度よりも低くてもよい。 The image area 101 displays an captured image (display screen image) acquired from the first recognition device 10. The image area 101 displays an captured image including the destination surface. The image resolution of the character string included in the captured image displayed by the image area 101 may be lower than the image resolution of the character string included in the captured image captured by the camera 3.
 入力欄102は、画像領域101の下部に形成されている。入力欄102は、画像領域101が表示する撮像画像に写る宛先面に記載されている宛先の入力を受け付ける。 The input field 102 is formed in the lower part of the image area 101. The input field 102 accepts the input of the destination described on the destination surface of the captured image displayed by the image area 101.
 また、入力画面100は、入力欄102への入力を確定するアイコンなどを備えてもよい。 
 また、入力欄102は、画像領域101の上部に形成されるものであってもよい。  入力画面の構成は、特定の構成に限定されるものではない。
Further, the input screen 100 may include an icon or the like for confirming the input to the input field 102.
Further, the input field 102 may be formed in the upper part of the image area 101. The configuration of the input screen is not limited to a specific configuration.
 入力画面を生成すると、プロセッサ21は、表示部インターフェース24を通じて生成した入力画面を出力する。プロセッサ21は、表示部インターフェース24に表示装置が接続されている場合と同様に入力画面を出力する。即ち、プロセッサ21は、表示部インターフェース24を通じて、ディスプレイなどの表示装置に出力する信号と同様の信号を出力する。 When the input screen is generated, the processor 21 outputs the input screen generated through the display unit interface 24. The processor 21 outputs an input screen in the same manner as when a display device is connected to the display unit interface 24. That is, the processor 21 outputs a signal similar to the signal output to a display device such as a display through the display unit interface 24.
 また、プロセッサ21は、操作部インターフェース23を通じて宛先の入力を受け付ける機能を有する。 Further, the processor 21 has a function of accepting the input of the destination through the operation unit interface 23.
 入力画面を出力すると、プロセッサ21は、操作部インターフェース23を通じて宛先の入力を受け付ける。プロセッサ21は、操作部インターフェース23に操作部が接続されている場合と同様の信号(キー入力操作を示す操作信号)を取得する。 When the input screen is output, the processor 21 receives the input of the destination through the operation unit interface 23. The processor 21 acquires the same signal (operation signal indicating a key input operation) as when the operation unit is connected to the operation unit interface 23.
 また、プロセッサ21は、入力を受け付けた宛先(宛先を示す情報)を第1の認識装置10に送信する機能を有する。 Further, the processor 21 has a function of transmitting an input-accepted destination (information indicating the destination) to the first recognition device 10.
 プロセッサ21は、操作部インターフェース23を通じて入力が確定する操作信号(たとえば、エンターキーが押された操作信号など)を受信すると、通信インターフェース25を通じて入力された宛先を第1の認識装置10に送信する。 When the processor 21 receives an operation signal whose input is confirmed through the operation unit interface 23 (for example, an operation signal for which the enter key is pressed), the processor 21 transmits the destination input through the communication interface 25 to the first recognition device 10. ..
 次に、第2の認識装置60が実現する機能について説明する。第2の認識装置60が実現する機能は、プロセッサ61がメモリ62などに格納されるプログラムを実行することで実現される。 Next, the functions realized by the second recognition device 60 will be described. The function realized by the second recognition device 60 is realized by the processor 61 executing a program stored in the memory 62 or the like.
 まず、プロセッサ61は、カメラ3から宛先面を含む撮像画像を取得する機能を有する。 
 プロセッサ61は、カメラインターフェース65を通じてカメラ3から撮像画像を取得する。プロセッサ61は、カメラ3から、第1の認識装置10が取得する撮像画像と同様の撮像画像を取得する。
First, the processor 61 has a function of acquiring an captured image including a destination surface from the camera 3.
The processor 61 acquires a captured image from the camera 3 through the camera interface 65. The processor 61 acquires an captured image similar to the captured image acquired by the first recognition device 10 from the camera 3.
 また、プロセッサ61は、OCR処理により撮像画像から宛先を取得する機能を有する。 Further, the processor 61 has a function of acquiring a destination from the captured image by OCR processing.
 撮像画像を抽出すると、プロセッサ61は、第1のアルゴリズムとは異なる所定のアルゴリズム(第2のアルゴリズム)に従って撮像画像にOCR処理を行う。第2のアルゴリズムは、第1のアルゴリズムが認識できない文字画像の少なくとも一部を認識することができる。 When the captured image is extracted, the processor 61 performs OCR processing on the captured image according to a predetermined algorithm (second algorithm) different from the first algorithm. The second algorithm can recognize at least a part of the character image that the first algorithm cannot recognize.
 OCR処理を行うと、プロセッサ61は、OCR処理の結果に基づいて物品の宛先面に記載されている宛先を取得する。 When the OCR processing is performed, the processor 61 acquires the destination described on the destination surface of the article based on the result of the OCR processing.
 なお、複数の撮像画像を取得した場合、プロセッサ61は、各撮像画像にOCR処理を行い、OCR処理の結果に基づいて宛先を取得する。 When a plurality of captured images are acquired, the processor 61 performs OCR processing on each captured image and acquires a destination based on the result of the OCR processing.
 宛先を取得すると、プロセッサ61は、撮像画像と宛先とを対応付けてメモリ62に格納する。たとえば、プロセッサ61は、撮像画像のファイル名として宛先を格納してもよい。なお、プロセッサ61は、撮像画像に画像IDなどを設定してもよい。 When the destination is acquired, the processor 61 associates the captured image with the destination and stores it in the memory 62. For example, the processor 61 may store the destination as the file name of the captured image. The processor 61 may set an image ID or the like in the captured image.
 また、プロセッサ61は、撮像画像と宛先とを対応付けてマッチング装置30へ送信する機能を有する。 Further, the processor 61 has a function of associating the captured image with the destination and transmitting the captured image to the matching device 30.
 プロセッサ61は、通信インターフェース66を通じてマッチング装置30から、撮像画像及び宛先を要求するリクエストを受信する。たとえば、リクエストは、所定の期間においてカメラ3が撮像した(又は、所定の期間においてプロセッサ61が取得した)撮像画像と当該撮像画像に対応する宛先とを要求する。 The processor 61 receives a request for a captured image and a destination from the matching device 30 through the communication interface 66. For example, the request requests an captured image captured by the camera 3 (or acquired by the processor 61 during a predetermined period) in a predetermined period and a destination corresponding to the captured image.
 プロセッサ61は、リクエストに従ってメモリ62から撮像画像及び宛先を取得する。撮像画像及び宛先を取得すると、プロセッサ61は、通信インターフェース66を通じて、撮像画像及び宛先を含むレスポンスをマッチング装置30に送信する。 The processor 61 acquires the captured image and the destination from the memory 62 according to the request. Upon acquiring the captured image and the destination, the processor 61 transmits a response including the captured image and the destination to the matching device 30 through the communication interface 66.
 次に、マッチング装置30が実現する機能について説明する。マッチング装置30が実現する機能は、プロセッサ31がメモリ32などに格納されるプログラムを実行することで実現される。 Next, the functions realized by the matching device 30 will be described. The function realized by the matching device 30 is realized by the processor 31 executing a program stored in the memory 32 or the like.
 まず、プロセッサ31は、VCS20から入力画面を取得する機能を有する。 
 プロセッサ31は、VCS20の表示部インターフェース24に接続する画像インターフェース33を通じて入力画面を取得する。即ち、プロセッサ31は、宛先面を含む撮像画像をVCS20から取得する。
First, the processor 31 has a function of acquiring an input screen from the VCS 20.
The processor 31 acquires an input screen through an image interface 33 connected to the display interface 24 of the VCS 20. That is, the processor 31 acquires the captured image including the destination surface from the VCS 20.
 また、プロセッサ31は、第2の認識装置60から撮像画像と当該撮像画像に対応する宛先とを取得する機能を有する。 Further, the processor 31 has a function of acquiring the captured image and the destination corresponding to the captured image from the second recognition device 60.
 プロセッサ31は、入力画面を取得した時刻に基づいて、当該入力画面に含まれる撮像画像がカメラ3に撮像された時刻を推定する。たとえば、プロセッサ31は、カメラ3が画像を撮像してから第1の認識装置10が宛先を認識し及びVCS20が入力画面を出力するまで時間に基づいて、カメラ3が撮像された時刻を推定する。ここでは、プロセッサ31は、カメラ3が撮像された時刻として、所定の幅を有する期間(推定期間)を推定する。たとえば、プロセッサ31は、入力画面を取得した時刻から所定の時間溯った時刻と、当該時刻から所定の時間が経過した時刻との間の期間を、推定期間として取得する。 The processor 31 estimates the time when the captured image included in the input screen is captured by the camera 3 based on the time when the input screen is acquired. For example, the processor 31 estimates the time when the camera 3 is imaged based on the time from when the camera 3 captures the image until the first recognition device 10 recognizes the destination and the VCS 20 outputs the input screen. .. Here, the processor 31 estimates a period (estimated period) having a predetermined width as the time when the camera 3 is imaged. For example, the processor 31 acquires, as an estimated period, a period between a time that is a predetermined time back from the time when the input screen is acquired and a time that a predetermined time has elapsed from the time.
 プロセッサ31は、通信インターフェース37を通じて、推定期間に撮像された撮像画像(候補撮像画像)と当該画像に対応する宛先とを要求するリクエストを送信する。プロセッサ31は、通信インターフェース37を通じて、当該候補撮像画像と当該宛先とを含むレスポンスを第2の認識装置60から受信する。 The processor 31 transmits a request for an image captured during the estimation period (candidate image) and a destination corresponding to the image through the communication interface 37. The processor 31 receives the response including the candidate captured image and the destination from the second recognition device 60 through the communication interface 37.
 また、プロセッサ31は、取得した候補撮像画像から入力画面に含まれる撮像画像を探索する機能を有する。即ち、プロセッサ31は、入力画面に含まれる撮像画像に対応する候補撮像画像を探索する。 Further, the processor 31 has a function of searching the captured image included in the input screen from the acquired candidate captured images. That is, the processor 31 searches for a candidate captured image corresponding to the captured image included in the input screen.
 プロセッサ31は、所定のアルゴリズムに従って、候補撮像画像と入力画面に含まれる撮像画像とをマッチングする。ここでは、プロセッサ31は、各候補撮像画像と入力画面に含まれる撮像画像との類似度を算出する。 The processor 31 matches the candidate captured image with the captured image included in the input screen according to a predetermined algorithm. Here, the processor 31 calculates the degree of similarity between each candidate captured image and the captured image included in the input screen.
 プロセッサ31は、最も高い類似度が所定の閾値を超えている場合、当該類似度に対応する候補撮像画像と入力画面に含まれる撮像画像とを同定する。 When the highest similarity exceeds a predetermined threshold value, the processor 31 identifies the candidate captured image corresponding to the similarity and the captured image included in the input screen.
 なお、プロセッサ31が候補撮像画像から入力画面に含まれる撮像画像を探索する方法は、特定の方法に限定されるものではない。 The method by which the processor 31 searches for the captured image included in the input screen from the candidate captured images is not limited to a specific method.
 また、プロセッサ31は、探索された候補撮像画像に対応する宛先をVCS20の操作部インターフェース23に入力する機能を有する。 Further, the processor 31 has a function of inputting a destination corresponding to the searched candidate captured image to the operation unit interface 23 of the VCS 20.
 入力画面に含まれる撮像画像の探索に成功すると、プロセッサ31は、当該撮像画像と同定した候補撮像画像に対応する宛先を取得する。宛先を取得すると、プロセッサ31は、入力インターフェース34を通じて、取得した宛先をVCS20の操作部インターフェース23に入力する。即ち、プロセッサ31は、宛先を入力するキー入力操作を示す操作信号を操作部インターフェース23に入力する。 When the search for the captured image included in the input screen is successful, the processor 31 acquires the destination corresponding to the captured image and the identified candidate captured image. When the destination is acquired, the processor 31 inputs the acquired destination to the operation unit interface 23 of the VCS 20 through the input interface 34. That is, the processor 31 inputs an operation signal indicating a key input operation for inputting a destination to the operation unit interface 23.
 また、プロセッサ31は、宛先の入力を完了する操作を示す操作信号を操作部インターフェース23に入力してもよい。 Further, the processor 31 may input an operation signal indicating an operation for completing the input of the destination to the operation unit interface 23.
 また、プロセッサ31は、入力画面に含まれる撮像画像の探索に失敗した場合、操作部40に入力された操作を示す操作信号を操作部インターフェース23に入力する機能を有する。 Further, the processor 31 has a function of inputting an operation signal indicating an operation input to the operation unit 40 to the operation unit interface 23 when the search for the captured image included in the input screen fails.
 たとえば、プロセッサ31は、最も高い類似度が所定の閾値を超えていない場合、入力画面に含まれる撮像画像の探索に失敗したと判定する。 For example, if the highest similarity does not exceed a predetermined threshold value, the processor 31 determines that the search for the captured image included in the input screen has failed.
 入力画面に含まれる撮像画像の探索に失敗した場合、プロセッサ31は、VCS20からの入力画面を表示部50に表示する。入力画面を表示部50に表示すると、プロセッサ31は、操作部40への入力を受け付ける。操作部40への入力を受け付けると、プロセッサ31は、入力された操作を示す操作信号を操作部インターフェース23に入力する。 If the search for the captured image included in the input screen fails, the processor 31 displays the input screen from the VCS 20 on the display unit 50. When the input screen is displayed on the display unit 50, the processor 31 accepts the input to the operation unit 40. Upon receiving the input to the operation unit 40, the processor 31 inputs an operation signal indicating the input operation to the operation unit interface 23.
 また、プロセッサ31は、表示部50に入力画面を更新してもよい。即ち、プロセッサ31は、表示部インターフェース24から入力画面をリアルタイムで取得し表示部50に表示する。 Further, the processor 31 may update the input screen on the display unit 50. That is, the processor 31 acquires the input screen from the display unit interface 24 in real time and displays it on the display unit 50.
 ここで、オペレータは、表示部50に表示される入力画面の画像領域を目視して宛先を操作部40に入力する。宛先の入力が完了すると、オペレータは、操作部40に、入力を完了する操作を入力する。 Here, the operator visually observes the image area of the input screen displayed on the display unit 50 and inputs the destination to the operation unit 40. When the input of the destination is completed, the operator inputs the operation to complete the input to the operation unit 40.
 なお、マッチング装置30に操作部40及び表示部50が接続されていない場合、プロセッサ31は、他のマッチング装置30に接続されている表示部50に入力画面を表示する。また、プロセッサ31は、当該他のマッチング装置30に接続されている操作部40に入力された操作を示す操作信号をVCS20の操作部インターフェース23に入力する。 When the operation unit 40 and the display unit 50 are not connected to the matching device 30, the processor 31 displays the input screen on the display unit 50 connected to the other matching device 30. Further, the processor 31 inputs an operation signal indicating an operation input to the operation unit 40 connected to the other matching device 30 to the operation unit interface 23 of the VCS 20.
 たとえば、主たるマッチング装置30(たとえば、マッチング装置30a)又は外部の制御装置は、入力に用いる操作部40及び入力画面を表示する表示部50を管理してもよい。 For example, the main matching device 30 (for example, the matching device 30a) or the external control device may manage the operation unit 40 used for input and the display unit 50 for displaying the input screen.
 次に、第1の認識装置10の動作例について説明する。 
 図7は、第1の認識装置10の動作例について説明するためのフローチャートである。
Next, an operation example of the first recognition device 10 will be described.
FIG. 7 is a flowchart for explaining an operation example of the first recognition device 10.
 まず、第1の認識装置10のプロセッサ11は、カメラインターフェース15を通じて物品の宛先面を含む撮像画像を取得する(S11)。撮像画像を取得すると、プロセッサ11は、第1のアルゴリズムに従って撮像画像にOCR処理を行う(S12)。 First, the processor 11 of the first recognition device 10 acquires an captured image including the destination surface of the article through the camera interface 15 (S11). When the captured image is acquired, the processor 11 performs OCR processing on the captured image according to the first algorithm (S12).
 OCR処理による宛先の取得に失敗すると(S13、NO)、プロセッサ11は、通信インターフェース16を通じて撮像画像をVCS20に送信する(S14)。撮像画像をVCS20に送信すると、プロセッサ11は、通信インターフェース16を通じて、VCS20から宛先を受信したかを判定する(S15)。 If the acquisition of the destination by the OCR process fails (S13, NO), the processor 11 transmits the captured image to the VCS20 through the communication interface 16 (S14). When the captured image is transmitted to the VCS 20, the processor 11 determines whether or not the destination has been received from the VCS 20 through the communication interface 16 (S15).
 VCS20から宛先を受信していないと判定すると(S15、NO)、プロセッサ11は、S15に戻る。 If it is determined that the destination has not been received from the VCS20 (S15, NO), the processor 11 returns to S15.
 OCR処理による宛先の取得に成功した場合(S13、YES)、又は、VCS20から宛先を受信したと判定した場合(S15、YES)、プロセッサ11は、OCR処理によって取得した宛先又はVCS20から受信した宛先に基づいて、ソータ2に物品の仕分先を設定する(S16)。 
 ソータ2に物品の仕分先を設定すると、プロセッサ11は、動作を終了する。
When the acquisition of the destination by the OCR processing is successful (S13, YES) or when it is determined that the destination is received from the VCS20 (S15, YES), the processor 11 determines the destination acquired by the OCR processing or the destination received from the VCS20. Based on the above, the sorter 2 is set to the supplier of the article (S16).
When the sorting destination of the article is set in the sorter 2, the processor 11 ends the operation.
 次に、VCS20の動作例について説明する。 
 図8は、VCS20の動作例について説明するためのフローチャートである。
Next, an operation example of the VCS 20 will be described.
FIG. 8 is a flowchart for explaining an operation example of the VCS20.
 まず、VCS20のプロセッサ11は、通信インターフェース25を通じて第1の認識装置10から撮像画像を受信したかを判定する(S21)。第1の認識装置10から撮像画像を受信していないと判定すると(S21、NO)、プロセッサ11は、S21に戻る。 First, the processor 11 of the VCS 20 determines whether or not the captured image has been received from the first recognition device 10 through the communication interface 25 (S21). If it is determined that the captured image has not been received from the first recognition device 10 (S21, NO), the processor 11 returns to S21.
 第1の認識装置10から撮像画像を受信したと判定すると(S21、YES)、プロセッサ21は、表示部インターフェース24を通じて撮像画像を含む入力画面を出力する(S22)。 When it is determined that the captured image has been received from the first recognition device 10 (S21, YES), the processor 21 outputs an input screen including the captured image through the display unit interface 24 (S22).
 入力画面を出力すると、プロセッサ21は、操作部インターフェース23を通じて宛先の入力を受け付けたかを判定する(S23)。宛先の入力を受け付けていないと判定すると(S23、NO)、プロセッサ21は、S23に戻る。 When the input screen is output, the processor 21 determines whether or not the input of the destination has been accepted through the operation unit interface 23 (S23). If it is determined that the input of the destination is not accepted (S23, NO), the processor 21 returns to S23.
 宛先の入力を受け付けたと判定すると(S23、YES)、プロセッサ21は、通信インターフェース25を通じて、入力された宛先を第1の認識装置10に送信する(S24)。入力された宛先を第1の認識装置10に送信すると、プロセッサ21は、動作を終了する。 When it is determined that the input of the destination has been accepted (S23, YES), the processor 21 transmits the input destination to the first recognition device 10 (S24) through the communication interface 25. When the input destination is transmitted to the first recognition device 10, the processor 21 ends the operation.
 次に、第2の認識装置60の動作例について説明する。 
 まず、第2の認識装置60が宛先を取得する動作例について説明する。
Next, an operation example of the second recognition device 60 will be described.
First, an operation example in which the second recognition device 60 acquires a destination will be described.
 図9は、第2の認識装置60が宛先を取得する動作例について説明するためのフローチャートである。 FIG. 9 is a flowchart for explaining an operation example in which the second recognition device 60 acquires a destination.
 まず、第2の認識装置60のプロセッサ61は、カメラインターフェース65を通じて物品の宛先面を含む撮像画像を取得する(S31)。撮像画像を取得すると、プロセッサ61は、第1のアルゴリズムに従って撮像画像にOCR処理を行う(S32)。 First, the processor 61 of the second recognition device 60 acquires an captured image including the destination surface of the article through the camera interface 65 (S31). When the captured image is acquired, the processor 61 performs OCR processing on the captured image according to the first algorithm (S32).
 OCR処理による宛先の取得に成功すると(S33、YES)、プロセッサ61は、撮像画像と宛先とを対応付けてメモリ62に格納する(S34)。 When the acquisition of the destination by the OCR process is successful (S33, YES), the processor 61 associates the captured image with the destination and stores the destination in the memory 62 (S34).
 OCR処理による宛先の取得に失敗した場合(S33、NO)、又は、撮像画像と宛先とを対応付けてメモリ62に格納した場合(S34)、プロセッサ61は、動作を終了する。 When the acquisition of the destination by the OCR process fails (S33, NO), or when the captured image and the destination are associated and stored in the memory 62 (S34), the processor 61 ends the operation.
 次に、第2の認識装置60が撮像画像及び宛先を送信する動作例について説明する。 Next, an operation example in which the second recognition device 60 transmits the captured image and the destination will be described.
 図10は、第2の認識装置60が撮像画像及び宛先を送信する動作例について説明するためのフローチャートである。 FIG. 10 is a flowchart for explaining an operation example in which the second recognition device 60 transmits a captured image and a destination.
 まず、第2の認識装置60のプロセッサ61は、通信インターフェース66を通じてマッチング装置30からリクエストを受信したかを判定する(S41)。リクエストを受信していないと判定すると(S41、NO)、プロセッサ61は、S41に戻る。 First, the processor 61 of the second recognition device 60 determines whether or not a request has been received from the matching device 30 through the communication interface 66 (S41). If it is determined that the request has not been received (S41, NO), the processor 61 returns to S41.
 リクエストを受信したと判定すると(S41、YES)、プロセッサ61は、受信したリクエストに従って撮像画像及び宛先をメモリ62から取得する(S42)。撮像画像及び宛先を取得すると、プロセッサ61は、通信インターフェース66を通じて撮像画像及び宛先を含むレスポンスをマッチング装置30に送信する(S43)。 
 レスポンスを送信すると、プロセッサ61は、動作を終了する。
When it is determined that the request has been received (S41, YES), the processor 61 acquires the captured image and the destination from the memory 62 according to the received request (S42). Upon acquiring the captured image and the destination, the processor 61 transmits a response including the captured image and the destination to the matching device 30 through the communication interface 66 (S43).
When the response is transmitted, the processor 61 ends the operation.
 次に、マッチング装置30の動作例について説明する。 
 図11は、マッチング装置30の動作例について説明するためのフローチャートである。
Next, an operation example of the matching device 30 will be described.
FIG. 11 is a flowchart for explaining an operation example of the matching device 30.
 マッチング装置30のプロセッサ31は、画像インターフェース33を通じて入力画面を取得したかを判定する(S51)。入力画面を取得していないと判定すると(S51、NO)、プロセッサ31は、S51に戻る。 The processor 31 of the matching device 30 determines whether or not the input screen has been acquired through the image interface 33 (S51). If it is determined that the input screen has not been acquired (S51, NO), the processor 31 returns to S51.
 入力画面を取得したと判定すると(S51、YES)、プロセッサ31は、入力画面を取得した時刻に基づく撮像画像(候補撮像画像)及び宛先を第2の認識装置60から取得する(S52)。 When it is determined that the input screen has been acquired (S51, YES), the processor 31 acquires the captured image (candidate captured image) and the destination based on the time when the input screen is acquired from the second recognition device 60 (S52).
 候補撮像画像及び宛先を取得すると、プロセッサ31は、各候補撮像画像から入力画面に含まれる撮像画像を探索する(S53)。 When the candidate captured image and the destination are acquired, the processor 31 searches for the captured image included in the input screen from each candidate captured image (S53).
 入力画面に含まれる撮像画像の探索に成功すると(S54、YES)、プロセッサ31は、当該撮像画像と同定した候補撮像画像に対応する宛先を取得する(S55)。宛先を取得すると、プロセッサ31は、入力インターフェース34を通じて宛先を入力するためのキー入力操作を示す操作信号をVCS20の操作部インターフェース23に入力する(S56)。 When the search for the captured image included in the input screen is successful (S54, YES), the processor 31 acquires the destination corresponding to the candidate captured image identified as the captured image (S55). When the destination is acquired, the processor 31 inputs an operation signal indicating a key input operation for inputting the destination through the input interface 34 to the operation unit interface 23 of the VCS 20 (S56).
 入力画面に含まれる撮像画像の探索に失敗すると(S54、NO)、プロセッサ31は、表示部50に入力画面を表示する(S57)。入力画面を表示すると、プロセッサ31は、操作部40に入力された操作を示す操作信号をVCS20の操作部インターフェース23に入力する(S58)。ここでは、プロセッサ31は、入力が完了した操作の入力を受け付けるまで、S58を実行する。 If the search for the captured image included in the input screen fails (S54, NO), the processor 31 displays the input screen on the display unit 50 (S57). When the input screen is displayed, the processor 31 inputs an operation signal indicating the operation input to the operation unit 40 to the operation unit interface 23 of the VCS 20 (S58). Here, the processor 31 executes S58 until it receives the input of the operation for which the input is completed.
 宛先を入力するためのキー入力操作を示す操作信号を操作部インターフェース23に入力した場合(S56)、又は、操作部40に入力された操作を示す操作信号を操作部インターフェース23に入力した場合(S58)、プロセッサ31は、動作を終了する。 When an operation signal indicating a key input operation for inputting a destination is input to the operation unit interface 23 (S56), or when an operation signal indicating an operation input to the operation unit 40 is input to the operation unit interface 23 (S56). S58), the processor 31 ends the operation.
 なお、マッチング装置30のプロセッサ31は、入力画面に含まれる撮像画像の探索に失敗した場合、推定期間を拡大して撮像画像及び宛先を第2の認識装置60から取得してもよい。プロセッサ31は、入力画面に含まれる撮像画像の探索を再度行う。 If the processor 31 of the matching device 30 fails to search for the captured image included in the input screen, the estimated period may be extended to acquire the captured image and the destination from the second recognition device 60. The processor 31 searches for the captured image included in the input screen again.
 また、プロセッサ31は、第2のアルゴリズムに従って、第2の認識装置60が取得した撮像画像にOCR処理を行い、宛先を取得してもよい。たとえば、第2の認識装置60のプロセッサ31は、カメラ3から撮像画像を取得すると、マッチング装置30の1つに撮像画像を送信する。マッチング装置30のプロセッサ31は、受信した撮像画像にOCR処理を行い、宛先を取得する。宛先を取得すると、プロセッサ31は、取得した宛先を第2の認識装置60に送信する。第2の認識装置60のプロセッサ61は、撮像画像と受信した宛先とを対応付けてメモリ62に格納する。 Further, the processor 31 may perform OCR processing on the captured image acquired by the second recognition device 60 according to the second algorithm to acquire the destination. For example, when the processor 31 of the second recognition device 60 acquires the captured image from the camera 3, the processor 31 transmits the captured image to one of the matching devices 30. The processor 31 of the matching device 30 performs OCR processing on the received captured image to acquire the destination. When the destination is acquired, the processor 31 transmits the acquired destination to the second recognition device 60. The processor 61 of the second recognition device 60 stores the captured image and the received destination in the memory 62 in association with each other.
 また、第2のアルゴリズムによるOCR処理は、マッチング装置30及び第2の認識装置60の両者で行われてもよい。 
 また、第2のアルゴリズムによるOCR処理は、外部装置によって実行されてもよい。たとえば、第2のアルゴリズムによるOCR処理は、クラウドコンピューティングによって実行される。この場合、第2の認識装置60のプロセッサ61は、外部装置に撮像画像を送信する。プロセッサ61は、外部装置からOCR処理の結果を取得する。
Further, the OCR processing by the second algorithm may be performed by both the matching device 30 and the second recognition device 60.
Further, the OCR processing by the second algorithm may be executed by an external device. For example, the OCR processing by the second algorithm is executed by cloud computing. In this case, the processor 61 of the second recognition device 60 transmits the captured image to the external device. The processor 61 acquires the result of the OCR process from the external device.
 また、第2の認識装置60の機能は、マッチング装置30の何れかが行ってもよい。  また、マッチング装置30は、複数の操作部及び表示部に接続するものであってもよい。 
 また、マッチング装置30は、操作部及び表示部と一体的に形成されるものであってもよい。
Further, the function of the second recognition device 60 may be performed by any of the matching devices 30. Further, the matching device 30 may be connected to a plurality of operation units and display units.
Further, the matching device 30 may be integrally formed with the operation unit and the display unit.
 また、第1の認識装置10は、VCS20と一体的に形成されるものであってもよい。 
 また、第1の認識装置10は、カメラ3と一体的に形成されるものであってもよい。  また、第1の認識装置10は、ソータ2と一体的に形成されるものであってもよい。
Further, the first recognition device 10 may be integrally formed with the VCS 20.
Further, the first recognition device 10 may be integrally formed with the camera 3. Further, the first recognition device 10 may be integrally formed with the sorter 2.
 また、VCS20は、操作部及び表示部を備えるものであってもよい。 
 また、認識システム1は、物品の宛先以外の文字列を認識するものであってもよい。認識システム1が認識する文字列は、特定の構成に限定されるものではない。
Further, the VCS 20 may include an operation unit and a display unit.
Further, the recognition system 1 may recognize a character string other than the destination of the article. The character string recognized by the recognition system 1 is not limited to a specific configuration.
 以上のように構成された認識システムは、第1の認識装置に接続するカメラから撮像画像を予め取得する。認識システム1は、予め第1の認識装置の第1のアルゴリズムと異なる第2のアルゴリズムに従って、撮像画像にOCR処理を行う。認識システムは、OCR処理の結果に基づく宛先を予めメモリなどに格納する。 The recognition system configured as described above acquires captured images in advance from the camera connected to the first recognition device. The recognition system 1 performs OCR processing on the captured image in advance according to a second algorithm different from the first algorithm of the first recognition device. The recognition system stores the destination based on the result of the OCR process in a memory or the like in advance.
 認識システムは、第1の認識装置が宛先の認識に失敗した撮像画像をVCSから取得する。認識システムは、予め取得した撮像画像からVCSからの撮像画像にマッチする撮像画像を探索する。認識システムは、探索された撮像画像に対応する宛先をVCSに入力する。 The recognition system acquires the captured image from the VCS in which the first recognition device fails to recognize the destination. The recognition system searches for an captured image that matches the captured image from the VCS from the captured image acquired in advance. The recognition system inputs the destination corresponding to the searched captured image into the VCS.
 その結果、認識システムは、第1の認識装置を改変することなく、効果的に宛先を取得することができる。 As a result, the recognition system can effectively acquire the destination without modifying the first recognition device.
 また、認識システムは、第2のアルゴリズムに従ったOCR処理に基づく宛先を予め格納することにより、高速にVCSに宛先を入力することができる。 Further, the recognition system can input the destination to the VCS at high speed by storing the destination based on the OCR processing according to the second algorithm in advance.
 また、カメラからの撮像画像の解像度がVCSからの撮像画像の解像度よりも低い場合であっても、認識システムは、高解像度の撮像画像に基づいて第2のアルゴリズムに従ったOCR処理を行うことができる。 Further, even when the resolution of the captured image from the camera is lower than the resolution of the captured image from the VCS, the recognition system performs OCR processing according to the second algorithm based on the high-resolution captured image. Can be done.
 本発明のいくつかの実施形態を説明したが、これらの実施形態は、例として提示したものであり、発明の範囲を限定することは意図していない。これら新規な実施形態は、その他の様々な形態で実施されることが可能であり、発明の要旨を逸脱しない範囲で、種々の省略、置き換え、変更を行うことができる。これら実施形態やその変形は、発明の範囲や要旨に含まれるとともに、特許請求の範囲に記載された発明とその均等の範囲に含まれる。 Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

Claims (9)

  1.  第1のアルゴリズムによる文字列の認識に失敗した撮像画像に含まれる文字列を入力するための入力装置から前記入力装置の表示画面に表示される少なくとも前記撮像画像に基づく表示画面画像を取得する画像インターフェースと、
     前記入力装置に文字列を入力する入力インターフェースと、
     画像取得装置からの前記撮像画像を取得する通信インターフェースと、
      前記表示画面画像に対応する前記撮像画像を探索し、
      前記第1のアルゴリズムと異なる第2のアルゴリズムによる、探索された前記撮像画像の文字認識処理の結果に基づく文字列を取得し、
      前記入力インターフェースを通じて、前記文字列を前記入力装置に入力する、
     プロセッサと、
    を備える情報処理装置。
    An image for acquiring at least a display screen image based on the captured image displayed on the display screen of the input device from an input device for inputting a character string included in the captured image in which recognition of the character string by the first algorithm fails. Interface and
    An input interface for inputting a character string into the input device,
    A communication interface that acquires the captured image from the image acquisition device, and
    Search for the captured image corresponding to the display screen image,
    A character string based on the result of the character recognition processing of the searched captured image by the second algorithm different from the first algorithm is acquired.
    Input the character string into the input device through the input interface.
    With the processor
    Information processing device equipped with.
  2.  前記通信インターフェースは、認識装置とデータを送受信し、
     前記プロセッサは、前記通信インターフェースを通じて、前記認識装置から前記撮像画像と前記撮像画像の文字認識処理の結果に基づく前記文字列とを取得する、
    請求項1に記載の情報処理装置。
    The communication interface sends and receives data to and from the recognition device.
    The processor acquires the captured image and the character string based on the result of character recognition processing of the captured image from the recognition device through the communication interface.
    The information processing device according to claim 1.
  3.  前記プロセッサは、前記通信インターフェースを通じて、前記表示画面画像を取得した時刻に基づく所定の期間において前記画像取得装置が撮像した前記撮像画像を取得する、請求項1又は2に記載の情報処理装置。 The information processing device according to claim 1 or 2, wherein the processor acquires the captured image captured by the image acquisition device in a predetermined period based on the time when the display screen image is acquired through the communication interface.
  4.  前記表示画面画像に含まれる文字列の画像解像度は、前記撮像画像に含まれる文字列の画像解像度よりも低い、
    請求項1乃至3の何れか1項に記載の情報処理装置。
    The image resolution of the character string included in the display screen image is lower than the image resolution of the character string included in the captured image.
    The information processing device according to any one of claims 1 to 3.
  5.  前記プロセッサは、前記入力インターフェースを通じて、前記文字列を入力するキー入力操作を示す操作信号を入力する、
    請求項1乃至4の何れか1項に記載の情報処理装置。
    The processor inputs an operation signal indicating a key input operation for inputting the character string through the input interface.
    The information processing device according to any one of claims 1 to 4.
  6.  操作部に接続する操作部インターフェースと、
     表示部に接続する表示部インターフェースと、
    を備え、
     前記プロセッサは、前記表示画面画像に対応する前記撮像画像の探索に失敗した場合、前記表示部インターフェースを通じて前記表示画面を前記表示部に表示し、前記入力インターフェースを通じて前記操作部に入力された操作を示す操作信号を前記入力装置に入力する、
    請求項1乃至5の何れか1項に記載の情報処理装置。
    The operation unit interface that connects to the operation unit and
    The display interface that connects to the display and
    With
    When the processor fails to search for the captured image corresponding to the display screen image, the processor displays the display screen on the display unit through the display unit interface, and performs an operation input to the operation unit through the input interface. The indicated operation signal is input to the input device.
    The information processing device according to any one of claims 1 to 5.
  7.  前記撮像画像は、物品の宛先が記載されている面を撮像した画像であり、
     前記プロセッサは、前記入力インターフェースを通じて、前記文字列として前記宛先を入力する、
    請求項1乃至6の何れか1項に記載の情報処理装置。
    The captured image is an image obtained by capturing a surface on which the destination of the article is described.
    The processor inputs the destination as the character string through the input interface.
    The information processing device according to any one of claims 1 to 6.
  8.  認識装置と情報処理装置とを備えるシステムであって、
     前記認識装置は、
      画像取得装置から撮像画像を取得する画像取得装置インターフェースと、
      前記情報処理装置とデータを送受信する第1の通信インターフェースと、
       第1のアルゴリズムと異なる第2のアルゴリズムに従って前記撮像画像に文字認識処理を行い、
       前記第1の通信インターフェースを通じて、前記撮像画像と文字認識処理の結果に基づく文字列とを前記情報処理装置に送信する、
      第1のプロセッサと、
     を備え、
     前記情報処理装置は、
      前記第1のアルゴリズムによる文字列の認識に失敗した前記撮像画像に含まれる文字列を入力するための入力装置から前記入力装置の表示画面に表示される少なくとも前記撮像画像に基づく表示画面画像を取得する画像インターフェースと、
      前記入力装置に文字列を入力する入力インターフェースと、
      前記認識装置とデータを送受信する第2の通信インターフェースと、
       前記第2の通信インターフェースを通じて、前記撮像画像を前記認識装置から取得し、
       前記表示画面画像に対応する前記撮像画像を探索し、
       前記第2の通信インターフェースを通じて、探索された前記撮像画像の文字認識処理の結果に基づく文字列を前記認識装置から取得し、
       前記入力インターフェースを通じて、前記文字列を前記入力装置に入力する、
      第2のプロセッサと、
     を備える、
    システム。
    A system equipped with a recognition device and an information processing device.
    The recognition device is
    An image acquisition device interface that acquires captured images from an image acquisition device, and
    A first communication interface for transmitting and receiving data to and from the information processing device,
    Character recognition processing is performed on the captured image according to a second algorithm different from the first algorithm, and the captured image is subjected to character recognition processing.
    Through the first communication interface, the captured image and a character string based on the result of the character recognition process are transmitted to the information processing apparatus.
    With the first processor
    With
    The information processing device
    Acquire at least a display screen image based on the captured image displayed on the display screen of the input device from the input device for inputting the character string included in the captured image that failed to recognize the character string by the first algorithm. Image interface and
    An input interface for inputting a character string into the input device,
    A second communication interface for transmitting and receiving data to and from the recognition device,
    The captured image is acquired from the recognition device through the second communication interface.
    Search for the captured image corresponding to the display screen image,
    Through the second communication interface, a character string based on the result of the character recognition processing of the searched captured image is acquired from the recognition device.
    Input the character string into the input device through the input interface.
    With the second processor
    To prepare
    system.
  9.  プロセッサによって実行される制御方法であって、
     画像取得装置から撮像画像を取得し、
     第1のアルゴリズムと異なる第2のアルゴリズムに従って前記撮像画像に文字認識処理を行い、
     前記第1のアルゴリズムによる文字列の認識に失敗した前記撮像画像に含まれる文字列を入力するための入力装置から前記入力装置の表示画面に表示される少なくとも前記撮像画像に基づく表示画面画像を取得し、
     前記表示画面画像に対応する前記撮像画像を探索し、
     探索された前記撮像画像の文字認識処理の結果に基づく文字列を前記入力装置に入力する、
    制御方法。
    A control method performed by a processor
    Acquire the captured image from the image acquisition device and
    Character recognition processing is performed on the captured image according to a second algorithm different from the first algorithm, and the captured image is subjected to character recognition processing.
    Acquire at least a display screen image based on the captured image displayed on the display screen of the input device from the input device for inputting the character string included in the captured image that failed to recognize the character string by the first algorithm. death,
    Search for the captured image corresponding to the display screen image,
    A character string based on the result of the character recognition process of the searched image is input to the input device.
    Control method.
PCT/JP2021/007965 2020-03-09 2021-03-02 Information processing device, system, and control method WO2021182185A1 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CA3169733A CA3169733A1 (en) 2020-03-09 2021-03-02 Information processing apparatus, system, and control method
EP21767087.6A EP4120128A4 (en) 2020-03-09 2021-03-02 Information processing device, system, and control method
AU2021235688A AU2021235688B2 (en) 2020-03-09 2021-03-02 Information processing apparatus, system, and control method
US17/929,845 US20220413623A1 (en) 2020-03-09 2022-09-06 Information processing apparatus, system, and control method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020039628A JP7443095B2 (en) 2020-03-09 2020-03-09 Information processing device, system and control method
JP2020-039628 2020-03-09

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/929,845 Continuation US20220413623A1 (en) 2020-03-09 2022-09-06 Information processing apparatus, system, and control method

Publications (1)

Publication Number Publication Date
WO2021182185A1 true WO2021182185A1 (en) 2021-09-16

Family

ID=77668750

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/007965 WO2021182185A1 (en) 2020-03-09 2021-03-02 Information processing device, system, and control method

Country Status (6)

Country Link
US (1) US20220413623A1 (en)
EP (1) EP4120128A4 (en)
JP (1) JP7443095B2 (en)
AU (1) AU2021235688B2 (en)
CA (1) CA3169733A1 (en)
WO (1) WO2021182185A1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005007315A (en) 2003-06-19 2005-01-13 Toshiba Corp Dividing machine and dividing method
JP2010009410A (en) * 2008-06-27 2010-01-14 Toshiba Corp Video coding system, classifying system, coding method and classifying method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3037691B1 (en) * 2015-06-16 2018-04-20 Solystic MATCHING PICTURES OF POSTAL ARTICLES WITH DESCRIPTORS OF SINGULARITES FROM THE GRADIENT FIELD

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005007315A (en) 2003-06-19 2005-01-13 Toshiba Corp Dividing machine and dividing method
JP2010009410A (en) * 2008-06-27 2010-01-14 Toshiba Corp Video coding system, classifying system, coding method and classifying method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4120128A4

Also Published As

Publication number Publication date
EP4120128A4 (en) 2024-01-24
EP4120128A1 (en) 2023-01-18
AU2021235688B2 (en) 2023-12-07
AU2021235688A1 (en) 2022-09-29
US20220413623A1 (en) 2022-12-29
CA3169733A1 (en) 2021-09-16
JP7443095B2 (en) 2024-03-05
JP2021140631A (en) 2021-09-16

Similar Documents

Publication Publication Date Title
US10078828B2 (en) Commodity registration apparatus and commodity registration method
JP2002255097A (en) Attitude determining device for artificial satellite
WO2021182186A1 (en) Recognition device and program
WO2021182185A1 (en) Information processing device, system, and control method
CN112368724A (en) Learning device, learning system, and learning method
US20180240093A1 (en) Information processing apparatus and information processing method
JP2009146245A (en) Image comparing method, apparatus and program
JP2014182618A (en) Sorting device and pattern recognition device
CN114139000A (en) Image retrieval system based on image global and local feature reordering
JP6947283B2 (en) Store equipment, store systems, image acquisition methods, and programs
JP7413219B2 (en) Information processing equipment and systems
JP6484603B2 (en) Information processing apparatus, system, information processing method, and program
US20230419698A1 (en) Information processing apparatus and information input system
JP2021043833A (en) Information processing apparatus
JP6625853B2 (en) Delivery management system
WO2023171622A1 (en) Recognition device, program, and system
JP7091974B2 (en) Image processing system, image processing device, image processing method, and image processing program
JP2023026154A (en) Information processing apparatus and program
JP2021192168A (en) Information processing apparatus, system, control method of information processing apparatus, and program
WO2022190900A1 (en) Image processing apparatus, program, and system
JP2014232436A (en) Delivery information management server and delivery information management system
JP2022045557A (en) Information processing device and program
JP2017174200A (en) Information output device, information output method, and information output program
JP2022077624A (en) Recognition device, recognition method, recognition system, and program
US20210027110A1 (en) Pattern recognition system, parameter generation method, and parameter generation program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21767087

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2021235688

Country of ref document: AU

ENP Entry into the national phase

Ref document number: 3169733

Country of ref document: CA

ENP Entry into the national phase

Ref document number: 2021235688

Country of ref document: AU

Date of ref document: 20210302

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021767087

Country of ref document: EP

Effective date: 20221010